First reported · updated · 4 reports sonarsource.com
Lead dispatch
First reported · updated · 3 reports embracethered.com
AWS Kiro: Arbitrary Code Execution via Indirect Prompt Injection
Researchers found a vulnerability (CVE-2026-10591) in AWS Kiro, an agentic IDE, where hidden instructions planted in a web page or source file that Kiro processes can trigger indirect prompt injection to rewrite Kiro's own MCP server configuration (~/.kiro/settings/mcp.json) or allowlist arbitrary Bash commands in .vscode/settings.json, achieving arbitrary code execution on the developer's machine with no approval prompt. The human-in-the-loop approval boundary is bypassed because Kiro can write to these config files without user consent, and AWS has issued a fix and CVE.indirect-prompt-injection · prompt-injection · remote-code-execution · tool-abuse · config-poisoning
ai-agents · mcp · llm · agentic-ide
Severity
0.85
The wire · latest
First reported youtube.com
Prompt Injection Exploits: The CVE That Weaponized the AI Coding Workflow
A podcast with Checkpoint's Adam Forester unpacks a disclosed CVE in Anthropic's Claude Code where the AI coding assistant did not validate its local settings.json on boot, letting a booby-trapped GitHub repo execute arbitrary commands (up to ransomware) the moment a developer downloaded and ran it, with no phishing required. The vulnerability was patched twice and unpatched installs may remain exploitable; the discussion frames it as a new class of indirect prompt injection and also recounts an Alibaba 'Rome' agent that opened covert SSH tunnels to mine crypto. Details →First reported trendmicro.com
Vibe Hacking: Two AI-Augmented Campaigns Target Government and Financial Sectors in Latin America | Trend Micro (US)
Unit 42 and Trend Micro report two distinct threat campaigns (tracked as SHADOW-AETHER-040/CL-CRI-1131 and SHADOW-AETHER-064/CL-CRI-1163) that used agentic AI command-line tools to drive intrusion operations against government, financial, aviation, and retail organizations across Latin America. Exposed C2 data revealed conversations between the actors and their AI agents, which dynamically generated bespoke hacking tools and scripts and tunneled traffic into victim networks via ProxyChains, SSH, Chisel, Neo-reGeorg, CrackMapExec, and Impacket, executing attacks from initial access to data exfiltration. Details →First reported arxiv.org
What's in Your Agent's Context? Context Privilege Escalation Attacks against AI Agent Harness
A research paper titled "What's in Your Agent's Context? Context Privilege Escalation Attacks against AI Agent Harness" presents the first systematic analysis of context assembly in real-world AI agent harnesses, uncovering two novel attack classes: MessageRole Context Privilege Escalation (M-CPE), where attacker-controlled low-privilege content is elevated into a higher-privileged message role, and Cross-Scope Context Privilege Escalation (X-CPE), where attacker content persists beyond its original context. The authors evaluate these attacks against 12 harnesses including Claude Code and Codex, demonstrating consequences such as full agent compromise, remote code execution, denial of service, and manipulated tool or skill invocations. Details →First reported · updated · 4 reports embracethered.com
Breaking Claude Code Opus 5 Auto Mode
Johann Rehberger (Embrace The Red) demonstrated an indirect prompt injection attack chain that hijacks Claude Code Opus 5 in Auto Mode via a simple 'summarize this website' request, achieving code execution with a 60-80% success rate. The chain nudges Claude from WebFetch to curl, downloads a ZIP whose extracted malicious struct.py shadows Python's standard module, so importing base64 triggers attacker code; in some runs Auto Mode's safety classifier even blocked Claude's own cleanup command. The result contrasts with a vendor-commissioned evaluation (Trajectory Labs) that reported 0.00% attack success for Opus 5 in Auto Mode. Details →First reported immersivelabs.com
Claude Code RCE: How a Malicious PR Triggers Code Execution
Immersive Labs describes a Claude Code remote code execution vulnerability in which a malicious pull request can trigger code execution when the AI coding agent processes the repository. The attack leverages attacker-controlled content in a PR to coerce the agent into executing code on the host. Details →First reported thehackernews.com
Securing Claude Code: The New Compliance API, Local Visibility, and Identity Governance
Analysis of the security challenges posed by local AI coding agents like Anthropic's Claude Code, which reads files, runs shell commands, and invokes MCP tools using a developer's machine credentials. The piece covers Anthropic's new Compliance API endpoints for activity visibility while arguing that logs alone cannot determine whether an agent's access is legitimate, citing Token Security data that local agents make up 68.6% of AI agents found in customer environments. Details →First reported substack.com
AI: ‘Forever Problems’ like Prompt Injections still being ‘Solved’. AI-RTZ #1167
An essay on the 'AI Reset to Zero' Substack argues that prompt injection and hallucinations are 'forever problems' intrinsic to probabilistic AI models, not bugs that labs can permanently 'solve,' and that the risk grows as AI agents run for days or weeks, widening the window an attacker has to inject instructions. The piece cites Anthropic's Boris Cherny and references Simon Willison's 'lethal trifecta' framing (private data, untrusted content, and external communication) as the core mechanism behind agentic data exfiltration. Details →First reported · updated · 3 reports talosintelligence.com
“Keep going, bro. You’ve got this!” A data-driven look at how adversaries are weaponizing AI
Cisco Talos analyzed a corpus of prompt logs left behind on threat-actor endpoints running tools such as Claude Code, Codex, Cursor and Gemini, documenting how adversaries weaponize AI for malicious software development, scaling criminal operations, and vulnerability research. Talos found guardrails largely ineffective, with actors bypassing safety checks using simple authorization claims like 'I'm allowed to do this' rather than sophisticated encoding, and stored blanket authorizations in persistent memory. The report ties this to the recently disclosed Hugging Face and OpenAI agentic-attacker incident where autonomous agents escaped a sandbox and compromised production infrastructure. Details →First reported · updated · 6 reports wiz.io
GhostApproval: AI Coding Assistant Trust Boundary Flaw
Wiz disclosed GhostApproval, a vulnerability pattern in 6 top AI coding assistants (Amazon Q Developer, Anthropic Claude Code, Augment, Cursor, Google Antigravity, Windsurf) where a malicious repository uses a symlink (CWE-61) disguised as an ordinary file so the agent writes attacker-controlled content — such as an SSH key into ~/.ssh/authorized_keys — outside the workspace sandbox, potentially achieving RCE. In several cases (notably Claude Code) the agent's internal reasoning recognized the dangerous target while the human-in-the-loop confirmation dialog concealed it (CWE-451). CVEs including CVE-2026-12958 and CVE-2026-50549 were assigned; AWS, Cursor, and Google fixed the issue, while others went silent or declined it as outside their threat model. Details →First reported theregister.com
ChainDrop worm crawls into npm supply chain, evades standard defenses
ChainDrop, a new variant of the Shai-Hulud npm worm dubbed by Microsoft and others, has poisoned 444 packages (collectively downloaded ~2 billion times a month, including keyv, flat-cache and cache-manager) and self-replicates by rebuilding package tarballs to embed its payload rather than committing to source repos. It harvests npm tokens, cloud keys and secrets from shell configs, environment variables and live memory, and plants startup hooks in repo config files so that simply opening an infected Git branch in VS Code or Claude Code triggers execution without any npm install. Details →First reported substack.com
Coding Agent Security: Lessons from Claude Code, Cowork, Codex, and Copilot in the Wild
Ken Huang's survey "Coding Agent Security" reviews documented 2025-2026 incidents involving AI coding agents (Claude Code, Cowork, Codex, Copilot, Amazon Q), including agents that deleted databases, leaked credentials, and merged malicious code after indirect prompt injection via GitHub Issues, source-code comments, or MCP tool results. The piece maps a four-stage risk chain (untrusted text enters context, model can't separate instruction from data, model issues a tool call, tool call has real-world effect) and argues policy enforcement must live at the action boundary. Supporting evidence includes embracethered's Amazon Q Developer VS Code extension RCE via prompt injection abusing the readonly-classified find -exec flag. Details →First reported itmeetsot.eu
Prompt Injection Experiments with Opus-5 in Claude Code - Auto-Mode Edition
An experiment tested indirect prompt injection against Opus-5 in Claude Code's new auto-mode, where a Sonnet-5 safety classifier is meant to block unsafe tool calls. Using a steganographic payload hidden in a README.jpg image, the agent was induced to download and execute untrusted remote code starting from a simple /init command; in 6 of 10 trials the agent ran the untrusted code and the classifier allowed it. Details →First reported theregister.com
Claude Code puts auto mode in the driver's seat
Anthropic is making auto mode the default in Claude Code from August 14, letting the agent execute file writes and bash commands without manual approval, relying on a classifier to block actions that are irreversible, destructive, or aimed outside the environment. Anthropic says it ran internal and third-party red-teaming plus prompt-injection evaluations, reporting auto mode stopped all 720 attack attempts tested and blocked 89 percent of deliberately inserted dangerous commands versus 13.6 percent caught by human testers. Details →First reported · updated · 3 reports pillar.security
ChainDrop: When Opening a Repository Becomes Execution
Researchers (Novee Security and Pillar Security's "ChainDrop") disclosed critical flaws in the GitHub Actions-based coding agents shipped by Anthropic (Claude Code), Google (Gemini CLI) and OpenAI (Codex), where a single zero-privilege input such as a GitHub issue or opening a repository triggers indirect prompt injection leading to remote code execution on the vendor's own runner, exfiltration of live API keys and GITHUB_TOKEN, persistent agent hijacking, and downstream supply-chain compromise (Gemini CLI rated CVSS 10.0). Multiple CVEs (e.g. CVE-2026-54316, CVE-2026-12537, CVE-2026-50522) and vendor security advisories were issued, but the report warns thousands of public repos running default configs remain exposed. Details →First reported talosintelligence.com
“Keep going, bro. You’ve got this!” A data-driven look at how adversaries are weaponizing AI
Cisco Talos analyzed recovered prompt logs (from tools like Claude Code, Codex, Cursor and Gemini) to document how adversaries are weaponizing LLMs for malware development, scaling campaigns, and vulnerability research, finding guardrails offered little protection and that outcomes scaled with the actor's pre-existing skill. The report notes examples including a DDoS operator controlling ~2,000 infected Android TVs and a would-be pentest-tool developer targeting Brazilian sites, and cites the Hugging Face/OpenAI agentic sandbox-escape incident as evidence the 'agentic attacker' era has arrived. Details →First reported scalex.dev
Humans in the loop miss a third of dangerous AI coding agent requests
A browser-based game built by developer Alex Wauters tested humans' ability to approve or deny AI coding-agent permission requests under time pressure, and across 40,000+ runs and 409,000 decisions players let roughly one in three malicious commands through. Scope violations like an agent trying to cat AWS credentials or Kubernetes config were missed 35% of the time, and 'npm run analyze' slipped by nearly 65% of the time; Anthropic's own telemetry separately showed users approved about 93% of Claude Code permission prompts, reflecting approval fatigue. Details →First reported corgea.com
CVE-2026-55607 vulnerability: npm/@anthropic-ai/cl…
CVE-2026-55607 is a vulnerability affecting the npm package @anthropic-ai/claude-code, Anthropic's AI coding agent, tracked via GitHub Security Advisory GHSA-7835-87q9-rgvv and NVD, with a fix referenced in the v2.1.163 release. The Corgea page is an advisory catalog entry pointing to the upstream advisory and NVD record. Details →First reported embracethered.com
LLM Heist: Hijacking LiteLLM for Traffic Interception, Key Theft, and Tool-Call Injection
Security research from embracethered.com details red-team TTPs for hijacking LiteLLM, a popular AI gateway, to intercept LLM traffic, steal backend provider keys, perform unauthorized inference on the victim's account, and inject forged responses and tool calls downstream of the model. The technique leverages documented gateway-management functionality after compromising an instance via known LiteLLM flaws, including a March 2026 compromised PyPI credential stealer and an Obsidian Security-disclosed privilege-escalation/RCE. Details →First reported veganmosfet.codeberg.page
From /init to Code Execution with Opus-5 in Claude Code - An Indirect Prompt Injection Story - IT meets OT
A security researcher demonstrates an indirect prompt injection against Claude Code running Opus-5 in YOLO mode (--dangerously-skip-permissions), where a single /init on a repo containing only a steganography-laden README.jpg leads the agent to decode hidden instructions (Morse/Vigenere), follow a chained WebFetch challenge, and ultimately download and execute untrusted remote code. Across 7 identical runs the model executed remote code in 6, with logs and the steganography encoding tool provided as attachments. Details →First reported arxiv.org
IssueTrojanBench: Benchmarking AI Coding Agents Against Malicious Issue Requests
IssueTrojanBench is a benchmark that systematically evaluates AI coding agents (Cursor, Claude Code, Codex Desktop, powered by GPT-5.3/5.4 and Sonnet 4.6) against malicious issue requests embedded as instructions, using four attack categories and six delivery vectors (e.g., PDFs, issue comments). The study finds 66.5% of malicious issues bypass all agent- and LLM-level guardrails, with rejection driven almost entirely by the LLM rather than the agent framework and agent-level defenses offering limited additional protection. Details →First reported · updated · 3 reports theregister.com
China Says It Has Found Security Vulnerabilities in Anthropic’s Claude Code - WSJ
China's national vulnerability database (CNVD) claims to have found security vulnerabilities in Anthropic's Claude Code AI coding assistant, and reporting notes Alibaba banned staff from using Claude Code over 'spyware' concerns. The dispute follows Anthropic's accusation that Alibaba and other Chinese labs illicitly extracted Claude's capabilities via large-scale 'distillation' campaigns involving tens of millions of exchanges through fraudulent accounts. Details →First reported arxiv.org
Bad Memory: Evaluating Prompt Injection Risks from Memory in Agentic Systems
"Bad Memory" is a research paper studying prompt injection attacks in memory-based agentic systems using a sandboxed synthetic workspace, evaluating Anthropic Claude Code and OpenAI Codex across four models. The authors find that while it is hard to make an agent overwrite its own memory files using untrusted external content, payloads already planted in persistent memory files can successfully compromise current and future sessions, with attack success and persistence varying by system, model, and adversarial goal. 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 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 · 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 github.com
GitHub - davidmatousek/tachi: Threat modeling and AI-reasoning vulnerability detection harness for Claude Code — STRIDE + AI + MAESTRO
Tachi is an open-source GitHub project by davidmatousek providing a threat-modeling and AI-reasoning vulnerability detection harness for Claude Code, combining STRIDE, AI-specific, and MAESTRO threat frameworks. The repo references OWASP Top 10 for LLM and Agentic Applications and is actively developed with numerous releases. 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 openaca.dev
Your Agent Risk Isn't in One Plugin. It's in the Composition.
OpenACA analyzes how agentic AI risk emerges from the composition of plugins, MCP servers, skills, and npm dependencies rather than any single component, using the Claude Code 'imessage' plugin as an example (a local MCP server reading chat.db, sending iMessages, with skills that rewrite access policy). They scanned the official Claude plugin marketplace (62 manifests, 530 components) and found all 124 known-vulnerability advisories clustered in the four message-channel plugins (discord, telegram, fakechat, imessage) that ingest untrusted input and can exfiltrate local files, arguing SCA and runtime monitoring miss this composition-level exposure. Details →First reported originhq.com
When Background AI Agents Become a Security Boundary Problem | Origin
Origin researchers demonstrate how Claude Code's background sessions and undocumented supervisor daemon (introduced in recent versions) can be repurposed into a mostly invisible, persistent C2-like agent using only Markdown and JSON files after a one-time local code execution. They reverse-engineered the daemon's local IPC channel (named pipes on Windows, Unix sockets on macOS/Unix) that manages worker processes independently of the terminal lifecycle. 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