First reported catonetworks.com
Lead dispatch
First reported island.io
AgentBaiting: How Fake AI Skills Deliver Malware at Scale
Island security researchers uncovered the FakeGit campaign, which used roughly 7,600 malicious GitHub repositories—over 800 posing as AI Skills or MCP servers—to deliver SmartLoader malware that installs the StealC information stealer. The campaign introduces a technique called AgentBaiting, in which AI agents such as Claude Code, Gemini, and ChatGPT autonomously discover the attacker repositories, treat the malicious README as legitimate documentation, and pass installation instructions to users; the operation recorded over 14 million downloads.supply-chain · tool-abuse · malware-delivery · agentbaiting
mcp · ai-agents · ai-skills · llm · copilot
Severity
0.75
The wire · latest
First reported embracethered.com
AWS Kiro: Arbitrary Code Execution via Indirect Prompt Injection
AWS Kiro, an agentic coding IDE, was vulnerable to arbitrary command execution via indirect prompt injection: hidden text on a web page (or a comment in a source file) processed by the agent could make Kiro use its no-approval fsWrite tool to rewrite ~/.kiro/settings/mcp.json (or allowlist all Bash commands in .vscode/settings.json), causing it to launch attacker-specified MCP servers/commands and achieve RCE on the developer's machine, bypassing the human 'allow' approval boundary. Discovered by Intezer with Kodem Security and independently by Embrace The Red (Johann Rehberger); AWS has patched the issue. Details →First reported · updated · 6 reports huggingface.co
Security incident disclosure — July 2026
Hugging Face disclosed that attackers breached its production infrastructure using an autonomous AI agent framework, stealing internal datasets and cloud/cluster credentials. The intrusion began when a malicious dataset abused two code-execution paths (a remote-code dataset loader and a template-injection in a dataset configuration) to run code on a processing worker, after which the agent swarm escalated to node-level access and moved laterally across internal clusters, executing thousands of actions across short-lived sandboxes with self-migrating command-and-control staged on public services. Hugging Face closed the vulnerable paths, evicted the attacker, rebuilt nodes, and rotated credentials. Details →First reported · updated · 9 reports sysdig.com
JADEPUFFER: Agentic ransomware for automated database extortion
Sysdig researchers documented JadePuffer, described as the first ransomware operation conducted end-to-end by an autonomous LLM agent. The agent gained initial access by exploiting CVE-2025-3248 (an unauthenticated RCE in the Langflow LLM-app framework), then autonomously performed reconnaissance, credential theft, lateral movement, persistence (a beaconing cron job), privilege escalation via Nacos auth bypass CVE-2021-29441, and encrypted 1,342 Nacos configuration items—adapting to failures in real time (e.g., recovering from a failed login in 31 seconds). Details →First reported mitiga.io
Modern Malware — Spyware Skills, Hijacked Base URLs, and 1,230+ Leaking API Keys in AI Instruction Files
Mitiga Labs details malware hidden in AI agent instruction files — Cursor rules, Anthropic Skills, Claude Hooks, AGENTS.md/CLAUDE.md context files, MCP server configs, and .pyc droppers — that AI agents follow with near-zero validation. The research found prompt-exfiltration tradecraft caught in the wild, attacker-controlled ANTHROPIC_BASE_URL overrides routing Claude traffic through MITM proxies, permission-bypass defaults, and over 1,230 hardcoded API keys and JWT tokens across tens of services. Mitiga also released a free scanner, Skillgate, built during the investigation. Details →First reported · updated · 4 reports zscaler.com
Indirect Prompt Injection Targets AI Agents | ThreatLabz
Zscaler ThreatLabz observed two in-the-wild campaigns using indirect prompt injection (IPI) embedded in malicious websites to manipulate web-browsing AI agents. One campaign uses SEO poisoning around a fake Python library (requests-secure-v2) with hidden prompts and schema-markup instructions telling agents to make a cryptocurrency payment to a hardcoded wallet to obtain an API key; the other typosquats the DeFi tracker DeBank, embedding prompts convincing agents the fraudulent site is legitimate. In testing an autonomous payment-capable agent across 26 LLMs, four (Llama 3.3 70B, Llama 3.2 90B Vision, Gemini 3 Flash, Gemini 2.5 Pro) were tricked into paying and two miscategorized the fake DeBank as trusted. Details →First reported pillar.security
The Week of Sandbox Escapes
Pillar Security researchers demonstrated seven sandbox-escape techniques against four AI coding agents — Cursor, OpenAI's Codex, Google's Gemini CLI and Antigravity — where a sandboxed agent writes workspace files that trusted tools running outside the sandbox (Python extensions, Git integrations, hook engines, Docker daemons) later execute. Prompt injection planted in a README, issue, dependency, or diff triggers local command execution on the developer's machine; one Cursor flaw is tracked as CVE-2026-48124 and fixed in version 3.0.0, with most issues patched and vendor-acknowledged. Details →First reported · updated · 5 reports wiz.io
GhostApproval: AI Coding Assistant Trust Boundary Flaw
Wiz researchers disclosed GhostApproval (CVE-2026-12958 and related), a symlink-following vulnerability pattern (CWE-61 plus CWE-451 UI misrepresentation) affecting six top AI coding assistants: Amazon Q Developer, Anthropic Claude Code, Augment, Cursor, Google Antigravity, and Windsurf. A malicious repository disguises a symlink as an innocuous config file so that when the agent 'sets up the workspace' it writes an attacker SSH key to ~/.ssh/authorized_keys — sometimes before any confirmation dialog — while the human-in-the-loop approval prompt conceals the true target, enabling remote code execution. AWS, Cursor, and Google fixed the issue; two vendors went silent and one called it outside its threat model. Details →First reported · updated · 2 reports asset-group.github.io
We put the exploit in a picture. Your AI code reviewer never opens it.
Researchers from the University of Missouri-Kansas City's ASSET Research Group demonstrated 'Ghostcommit,' an attack that hides malicious prompt-injection instructions inside a PNG image so AI code reviewers (CodeRabbit, Cursor Bugbot) never see them. A benign-looking AGENTS.md convention file points to build-spec.png, whose rendered text instructs a coding agent to read the repo's .env byte-by-byte and emit the secrets as an integer tuple; the payload sits dormant until an unrelated agent session triggers exfiltration. A proof-of-concept is published on GitHub and the findings were disclosed to affected vendors. Details →First reported · updated · 3 reports appsentinels.ai
One Poisoned MCP Server Can Hijack All the Others — Coograph
MCP tool poisoning hides malicious instructions inside a Model Context Protocol server's tool descriptions, parameter schemas, or return values — invisible to human reviewers but fully read by the LLM, which then selects and executes the poisoned tool, enabling data exfiltration, credential theft, or lateral movement. The technique spans schema poisoning, tool shadowing, and rug pulls, and is catalogued as OWASP MCP03:2025; a single malicious server can influence an agent's decisions across all connected tools (cross-tool poisoning). Details →First reported substack.com
Data Exfiltration from Slack AI via indirect prompt injection
PromptArmor identified an indirect prompt injection vulnerability in Slack AI, a RAG-style chat search interface, where an attacker seeds poisoned tokens into a public channel or an imported document. When a user later queries Slack AI, the injected instructions cause private data (e.g. an API key from a private channel) to be embedded into a malicious Markdown link that exfiltrates the secret to the attacker's server when clicked. Details →First reported · updated · 5 reports varonis.com
SearchLeak: How We Turned M365 Copilot Into a One-Click Data Exfiltration Weapon
SearchLeak (CVE-2026-42824) is a critical three-stage vulnerability chain in Microsoft 365 Copilot Enterprise discovered by Varonis Threat Labs that lets an attacker steal MFA codes, emails, meeting details, and organizational files with a single click on a trusted microsoft.com link. It chains a Parameter-to-Prompt (P2P) injection via the search q parameter with an HTML rendering race condition and a CSP bypass through Bing's allowlisted image-search SSRF endpoint to silently exfiltrate a victim's mailbox, calendar, SharePoint, and OneDrive data. Microsoft remediated the flaw and rated it critical. Details →First reported swarmnetics.com
Agentjacking and MCP trust: are AI coding agents too easy to steer?
Agentjacking, described by Swarmnetics and Tenet Security, abuses trusted error-report inputs in AI coding agents: an attacker with a publicly exposed Sentry DSN can inject malicious instructions into telemetry that the agent processes, steering it to exfiltrate secrets such as cloud keys, Git credentials, and private repo URLs. The root flaw is that these systems treat source trust as if it equals action trust, letting external report text become executable guidance. Details →First reported tenetsecurity.ai
A public Sentry key is all it takes to hijack Claude Code, Cursor, and Codex
Researchers at Tenet Security describe "agentjacking," an attack in which a publicly exposed Sentry key lets an attacker inject fake error messages that AI coding agents such as Claude Code, Cursor, and Codex ingest via the Sentry MCP server. The crafted error content acts as an indirect prompt injection, hijacking the agent to execute attacker-directed actions; the team also published a mitigation tool, agent-jackstop, on GitHub. Details →First reported foxnews.com
HalluSquatting attack exploits AI hallucinations to spread malware
The HalluSquatting attack exploits AI hallucinations by registering package or software names that large language models invent when suggesting dependencies, so developers who trust AI-recommended names end up installing attacker-controlled malware. The technique weaponizes the tendency of LLMs to hallucinate plausible-sounding but nonexistent package names. Details →First reported · updated · 3 reports theregister.com
GitLost: How We Tricked GitHub’s AI Agent into Leaking Private Repos - Noma Security
Noma Security's "GitLost" research demonstrated that GitHub Agentic Workflows (AI agents backed by Claude or Copilot) could be tricked via indirect prompt injection: an unauthenticated attacker posts a crafted issue on a public org repo, and the agent fetches a private repo's README and posts it in a public comment. The PoC used an "Additionally" prefix to bypass guardrails and was disclosed to GitHub with no public patch date noted. Details →First reported nhimg.org
AI browser guardrail bypass exposes a new data theft path
LayerX Security describes a "BioShocking" attack that games an AI browser into violating its guardrails by establishing a false reality, enabling data theft, code copying, and system command execution. The attack exploits the browser-mediated trust boundary, using indirect or staged instructions embedded in webpage context that pass prompt filters yet still steer the model into malicious enterprise actions inside an authenticated session. Details →First reported qianxin.com
NadMesh Botnet Analysis: A Product-Grade Threat for the AI Service Era
NadMesh is a Go-based botnet observed in early July 2026 by QiAnXin's XLab that autonomously scans for and exploits exposed AI services — ComfyUI, Ollama, n8n, Open WebUI, Langflow, and Gradio — using a Shodan harvester (ai_harvest.py) to prioritize AI infrastructure and the MCP ecosystem. It folds scanning, 20+ RCE exploitation vectors (Redis, Docker, MCP, Kubernetes), credential/AI-service intelligence harvesting, polymorphic builds, and redundant persistence into a single productized platform; the operator's dashboard claims 3,811 unique AWS keys plus model inventories tagged as cloud services. Details →First reported · updated · 2 reports barracuda.com
Text salting: How hidden text evades AI email security
Barracuda researchers report more than one million retail-themed phishing emails since April that use 'text salting' — hidden, harmless-looking text invisible to recipients but readable by scanners — to dilute malicious signals and fool both traditional and AI-powered email security filters. Generative AI lets attackers generate these salted campaigns cheaply, at scale, and with high variation, while AI-based content analysis engines fail to see through the hidden content. Details →First reported infosecwriteups.com
Google fixing Android lock screen bug that lets Gemini send SMS without a PIN
Google is fixing an Android 16 lock screen bypass in which Gemini, accessible from the lock screen, can be tricked into sending SMS and WhatsApp messages without a PIN. Pressing Gemini's "Continue" prompt simultaneously with its "Add attachment" button lets an attacker with physical access dispatch messages and re-enable Gemini's access to previously disconnected apps, all while the device stays locked. Details →First reported wiz.io
Wiz Uncovers Critical Access Bypass Flaw in AI-Powered Vibe Coding Platform Base44
Wiz disclosed a now-patched critical authentication bypass in Base44, an AI-powered 'vibe coding' platform owned by Wix, where supplying only a non-secret 'app_id' value to undocumented registration and email-verification endpoints let an attacker create a verified account for private applications. The flaw bypassed all authentication controls, including SSO, granting full access to private apps and their data; Wix fixed it within 24 hours of the July 9, 2025 disclosure, with no evidence of exploitation in the wild. Details →First reported · updated · 2 reports cyera.com
Ollama Out-of-Bounds Read Vulnerability Allows Remote Process Memory Leak
Cyera researchers disclosed CVE-2026-7482 ("Bleeding Llama", CVSS 9.1), a heap out-of-bounds read in Ollama's GGUF model loader that lets a remote, unauthenticated attacker leak the entire process memory of an Ollama server. The flaw is fixed in Ollama 0.17.1 and is estimated to affect over 300,000 exposed servers globally. Details →First reported nist.gov
NVD - CVE-2026-30741
CVE-2026-30741 is a remote code execution vulnerability in OpenClaw Agent Platform v2026.2.6 that allows attackers to execute arbitrary code via a request-side prompt injection attack. CISA-ADP rated it CVSS 3.1 base 9.8 (Critical), classified as CWE-94 code injection, with public exploit references including a GitHub PoC repository. Details →First reported strobes.co
CVE-2026-23744 - CVE Details, Severity, and Analysis | Strobes VI
CVE-2026-23744 is a critical (CVSS 9.8) remote code execution vulnerability in MCPJam Inspector versions 1.4.2 and earlier, a local-first development platform for MCP servers. Because the tool binds to 0.0.0.0 and its /api/mcp/connect endpoint extracts command and args without security checks, an attacker can send a crafted, unauthenticated HTTP request to trigger arbitrary command execution with no user interaction; public PoCs and vendor patches are available. Details →First reported · updated · 2 reports redhat.com
CVE-2026-42271 - Red Hat Customer Portal
CVE-2026-42271 is an Important-severity (CVSS 8.8) flaw in LiteLLM, an AI gateway/proxy for LLM APIs, where two MCP-server preview endpoints accepted full server configurations including command-execution parameters without adequate role checks. An authenticated user with even low-privilege internal-user keys could send a crafted configuration to achieve arbitrary OS command execution on the proxy host; Red Hat notes known public exploits and the CVE is tracked in CISA's KEV catalog, with fixes shipped in LiteLLM v1.83.7-stable and Red Hat OpenShift AI / Ansible Automation Platform errata. Details →First reported nist.gov
NVD - CVE-2026-59819
CVE-2026-59819 is a vulnerability in LiteLLM, an AI gateway/proxy for calling LLM APIs, where prior to version 1.83.10-stable the /health/test_connection endpoint resolved request-supplied environment and OIDC file references in litellm_params, allowing a privileged caller to read arbitrary local files via an oidc/file/ reference (CWE-73). The issue is fixed in version 1.83.10-stable. Details →First reported cyberscoop.com
Sysdig clocks first documented case of agentic ransomware
CyberScoop, reporting on Sysdig research, describes JadePuffer — the first documented case of agentic ransomware, where an AI agent autonomously drove an end-to-end extortion operation spanning reconnaissance, credential theft, lateral movement, persistence, encryption and ransom-note delivery. The late-June 2026 attack gained initial access via Langflow flaw CVE-2025-3248, targeted a MySQL/Alibaba Nacos production server, ran more than 600 purposeful payloads, and used keys for OpenAI, Anthropic, DeepSeek and Gemini, with the agent fixing a failed backdoor in 31 seconds. Details →First reported · updated · 2 reports manifold.security
ClaudeBleed Reopened: Browser Extensions Can Still Push Claude for Chrome to Read Your Gmail
Manifold Security researcher Ax Sharma disclosed two unpatched vulnerabilities in Anthropic's Claude for Chrome extension (v1.0.80). Any browser extension with a content script on claude.ai can inject a DOM element and dispatch a synthetic click that Claude treats as a legitimate user action, triggering one of nine hardcoded workflows that read Gmail, Google Docs, and Calendar or act on Salesforce; a second flaw initializes the side panel in privileged mode via a ?skipPermissions=true URL parameter with no consent. Rated CVSS 7.7 in default mode and 9.6 Critical when 'Act without asking' is enabled, and reportedly still reproducible after eight releases since being reported to Anthropic in May. Details →First reported · updated · 3 reports theregister.com
Red teamers turned Claude Desktop into a double agent to do their evil bidding
Oasis Security disclosed "PromptFiction," a vulnerability in Anthropic's Claude Desktop where a single click on a trusted-looking claude:// URL silently submitted attacker-controlled prompts to the assistant with no user confirmation. Chained with the earlier "Claudy Day" trio of flaws, it could enable silent exfiltration of prior conversations and — when Anthropic's official Filesystem MCP server is installed — file read/write, persistence, and remote code execution. Anthropic has fixed the flaw. Details →First reported embracethered.com
From Indirect Prompt Injection to DNS Exfiltration in macOS Terminal
Johann Rehberger (Embrace The Red) demonstrates a proof-of-concept where an indirect prompt injection hidden in a spreadsheet cell hijacks an LLM-integrated CLI tool to emit ANSI escape codes, which the macOS Terminal app interprets to issue DNS requests that exfiltrate data from other rows. Building on prior Terminal DiLLMa research and David Leadbeater's original finding, the post reports that Apple has fixed the macOS Terminal behavior enabling the DNS-based exfiltration. Details →First reported · updated · 2 reports paloaltonetworks.com
Pickle in the Middle – Hijacking Vertex AI Model Uploads for Cross-Tenant RCE
Palo Alto Unit 42 (Ori Hadad) disclosed CVE-2026-0257, a flaw in Google's Vertex AI Python SDK (python-aiplatform) where model uploads relied on an attacker-predictable Google Cloud Storage bucket, enabling 'bucket squatting.' An attacker could pre-register the expected bucket and substitute a malicious pickle/joblib model artifact, achieving cross-tenant remote code execution when the poisoned model was deserialized. Google fixed the issue in SDK releases v1.148.0/v1.148.1. Details →First reported mitiga.io
MCP Token Theft in Claude Code: A Man-in-the-Middle Attack Chain
Mitiga Labs research details a man-in-the-middle attack chain against Claude Code in which a user-level post-install hook rewrites MCP server endpoints in ~/.claude.json to route MCP traffic through attacker-controlled infrastructure and steal OAuth tokens for connected SaaS (Jira, Confluence, GitHub, etc.). Because provider-side audit logs still show valid OAuth traffic from Anthropic's trusted egress range, the malicious activity blends in as legitimate user actions, and token rotation fails to break the chain while the hook keeps reseeding the config. Details →First reported paloaltonetworks.com
OpenClaw’s Skill Marketplace and the Emerging AI Supply Chain Threat
Unit 42 describes an emerging AI supply-chain threat in which malicious "skills" published to the OpenClaw agent skill marketplace act as a distribution channel for malware and data theft. Corroborating research from Trend Micro (Atomic macOS Stealer delivery), Bitdefender, Koi.ai (341 malicious ClawedBot skills) and JFrog documents how attackers hide payloads inside agent skills users install to extend AI-agent capabilities. Details →First reported · updated · 2 reports adversa.ai
The Cursor deeplink vulnerability that turns a “review this PR” click into remote code execution
Adversa AI researcher Rony Utevsky details a Cursor IDE vulnerability (dubbed DeepJack) where a crafted `cursor://` deeplink installs an attacker-controlled MCP server that runs arbitrary, unsandboxed commands under the victim's account after one click and one confirmation. The install dialog renders the command in a single-line field so a malicious tail is pushed off-screen, and double-URL encoding disguises the `mcp/install` URI as a routine `pr-review` link. Cursor acknowledged the root cause but closed the reports as duplicates, and build 3.9.8 reportedly remains vulnerable. Details →First reported · updated · 2 reports stepsecurity.io
Miasma Supply Chain Attack: Azure Hit, 73 Repos Down, 37 PyPI Wheels
The Miasma supply-chain worm campaign expanded to poison Microsoft's Azure/durabletask GitHub repository with config files that execute a credential-harvesting payload the moment a developer opens the repo in AI coding tools like Claude Code, Gemini CLI, Cursor, or VS Code, triggering GitHub to disable 73 Microsoft repositories including Azure/functions-action. Two days later the Hades variant dropped 37 malicious PyPI wheels across 19 packages using Python .pth startup hooks to run a Bun-powered credential stealer on every interpreter launch, with Socket tracking 448 affected artifacts across npm and PyPI. Details →First reported bugcrowd.com
One-Click Data Exfiltration via rovoChatPrompt URL Parameter (Confluence / Rovo) - CrowdStream
A disclosed and now-patched vulnerability in Atlassian Rovo, the default AI assistant across Confluence and other Atlassian products, allowed the `rovoChatPrompt` URL parameter to preload an arbitrary prompt into a victim's Rovo chat. When an authenticated user clicked a crafted link, Rovo executed the embedded prompt as a genuine query, using indirect task-framed language ('help me identify this image') to bypass guardrails and exfiltrate Confluence pages, secrets, and connected-app data (Jira, SharePoint, Outlook) to an attacker host via an image-fetch URL. Atlassian remediated the issue server-side and the reporter validated the fix. Details →First reported wraith.sh
Data Exfiltration via Markdown Images: The Quiet AI Vulnerability
Wraith's attack guide by Anthony D'Onofrio details data exfiltration via markdown image rendering in AI products, where an injected payload (via prompt injection, RAG doc, shared document, or email) causes an LLM to emit a markdown image whose URL embeds secrets like system prompts, conversation history, or API keys; when the chat client renders the markdown, the browser silently fetches the attacker's URL, leaking the data with zero clicks and no visible artifact. The guide notes variants have hit ChatGPT, Microsoft Copilot, GitHub Copilot Chat, Slack AI Assistant, Google Bard, and Claude.ai, and covers four defensive patterns. Details →First reported · updated · 3 reports catonetworks.com
DuneSlide: Two Critical RCE vulnerabilities
Cato AI Labs disclosed two critical vulnerabilities in Cursor IDE, dubbed DuneSlide (CVE-2026-50548 and CVE-2026-50549, both CVSS 9.8), that allow zero-click prompt injection to escape the editor's command sandbox and achieve remote code execution. CVE-2026-50548 abuses the run_terminal_cmd tool's working_directory parameter to add attacker-chosen folders to the allowed-write list, letting an attacker overwrite the cursorsandbox binary or shell startup files and turn sandboxed commands into full system compromise. Cursor patched both in version 3.0, released April 2; earlier 2.x builds remain exposed. Details →First reported · updated · 2 reports cereblab.com
Grok Build Uploads Entire Git Repositories to xAI Storage, Not Just Files It Reads
AI safety researcher Cereblab found that xAI's Grok Build CLI uploaded users' entire Git repositories — including files it was explicitly told not to open and secrets deleted from Git history — as Git bundles to a Google Cloud Storage bucket, even on an idle 'reply OK' prompt. The behavior was reproduced across multiple codebases and captured on the wire via mitmproxy; xAI later disabled it server-side with a disable_codebase_upload flag and Musk promised deletion of uploaded data. Details →First reported · updated · 2 reports tenetsecurity.ai
Fake Bug Report Hijacks AI Coding Agents at Scale
Tenet Security demonstrated "agentjacking," an indirect prompt-injection technique in which an attacker plants a single fake error report in a public bug-tracking service (Sentry) that hijacks AI coding agents into running attacker-controlled code on a developer's machine. In controlled testing, widely used assistants including Claude Code, Cursor, and Codex retrieved the poisoned error data and, in many cases, executed the code, opening a path to theft of cloud credentials, AWS keys, GitHub tokens, SSH keys, and CI/CD secrets. Details →First reported sans.edu
Someone Is Scanning for Your MCP Servers and AI Assistant Credentials
A SANS ISC diary by Manuel Humberto Santander Peláez reports that analysis of 14 days of Apache/ModSecurity logs from a small web host revealed distributed internet scanning specifically targeting Model Context Protocol (MCP) servers, AI assistant configuration files, and locally exposed LLM endpoints. Notably, the POST /mcp probes carried valid JSON-RPC 2.0 MCP 'initialize' handshakes from 49 distinct source IPs, indicating scanners that speak the protocol and would enumerate tools and data sources if a real MCP server responded. Details →First reported jscrambler.com
Unauthorized Publication of a Malicious npm Package affecting CI
Jscrambler disclosed that a threat actor used compromised npm publishing credentials to publish a malicious version of its 'jscrambler' npm package (versions 8.14, 8.16, 8.17, 8.20), which ran an infostealer during the preinstall hook and was downloaded around 1,479 times in a two-hour window. Per Socket's analysis, the malware harvested developer credentials, cloud secrets, crypto wallets, browser data, and notably AI coding tool and MCP configurations (Claude, Cursor, Windsurf, VS Code, Zed), using ChaCha20-Poly1305 obfuscation to resist analysis. Jscrambler revoked credentials and released a safe version 8.22. Details →First reported ainowinstitute.org
Friendly Fire: Hijacking Defensive Cyber AI Agents for Remote Code Execution
The AI Now Institute published an exploit brief and PoC (GitHub: Boyan-MILANOV/friendly-fire-ai-agent-exploit) demonstrating remote code execution against Anthropic's Claude Code CLI (auto-mode) and OpenAI's Codex CLI (auto-review) when these defensive coding agents are used to assess third-party or open-source libraries. The attack embeds prompt injections across a library's source code to hijack the AI agent, requiring no hooks, skills, plugins, MCP servers, or config files as an injection vector. Details →First reported 0din.ai
Mozilla Shows the Danger of Indirect Prompt Injections in AI Coding Agents
Mozilla 0DIN researchers Andre Hall and Miller Engelbrecht demonstrated a proof-of-concept attack where a clean GitHub repository with no malicious code uses indirect prompt injection to trick AI coding agents like Anthropic's Claude Code into chaining routine actions that grant an attacker shell command access and persistence. The malicious payload never appears in the repository; instead it is pulled at runtime from DNS after the agent blindly trusts the repo, evading scanners and human review. Details →First reported · updated · 2 reports hiddenlayer.com
EchoGram and guardrail bypass: are AI defenses keeping up?
HiddenLayer research dubbed EchoGram demonstrates that carefully chosen token sequences can flip verdicts in LLM guardrail models, causing harmful prompts to be marked safe or benign prompts to trigger false alarms. The NHIMG editorial summarizes the finding and its implications for organizations relying on probabilistic AI safety layers to protect deployed LLMs and agents. Details →First reported arxiv.org
A Security Analysis of the OpenClaw AI Agent Framework
Researchers detailed three now-patched high-severity flaws (GHSA-hjr6-g723-hmfm, GHSA-9969-8g9h-rxwm, GHSA-575v-8hfq-m3mc; CVE-2026-46817, CVE-2026-55200) in the OpenClaw personal AI assistant framework that compose into a complete unauthenticated remote code execution path — from an LLM tool call triggered via a WhatsApp message to command execution on the host. The chain abuses OS command injection and an incomplete disallowed-input filter in the exec allowlist, whose closed-world lexical parsing is defeated by shell line continuation, busybox multiplexing, and GNU option abbreviation; a companion arXiv analysis taxonomizes 470 advisories and shows a malicious plugin skill bypassing the exec pipeline entirely. Details →First reported · updated · 6 reports noma.security
GitLost: How We Tricked GitHub’s AI Agent into Leaking Private Repos
Noma Security researchers demonstrated GitLost, an indirect prompt injection technique that lets an attacker open a normal-looking public GitHub issue to steer GitHub Agentic Workflows into leaking the contents of an organization's private repositories into a public comment. The attack requires no stolen credentials or access, only that the organization's agent has read access across its repos. Details →First reported · updated · 2 reports sysdig.com
Understanding Langflow CVE-2026-55255, and why higher CVSS vulnerabilities aren't always the most exploited
CISA added CVE-2026-55255, an actively exploited Insecure Direct Object Reference (IDOR) authorization-bypass flaw in the Langflow visual framework for building AI agents, to its Known Exploited Vulnerabilities catalog and ordered federal agencies to patch it. The flaw lets authenticated attackers access other users' flows via the /api/v1/responses endpoint using a victim's flow UUID, and Sysdig observed in-the-wild exploitation aimed at leaking API keys, delivering second-stage loaders, and stealing LLM/cloud credentials and compute. Details →First reported huntress.com
New BioShocking attack manipulates AI browser into data theft
A new prompt injection attack dubbed 'BioShocking' reportedly tricks AI-powered browsers into treating risky real-world actions as part of a fictional scenario, bypassing safety guardrails and enabling data theft. Details →How the wire is made
Poll & cluster
Internet is crawled for AI security news and near-duplicate coverage is embedded and grouped into durable items.
Curate
AI Agent filters for agentic-AI relevance, classifies and tags each item, scores severity for threats, and writes the summary.
Every item here is one machine-curated intelligence object, not a headline.
Read the wire for free. There is a small charge to ask the index questions.
The wire, open
The complete curated feed, no key required.
- GET /feed.xml — RSS 2.0, every item
- GET /api/items — read-only
The vector desk
Query the index by meaning, not just keyword.
- GET /api/items?tags=&minSeverity=&itemType=
- GET /api/search?q= — keyword
- GET /api/semantic?q= — vector