First reported youtube.com
Analysis · latest
First reported deepinspect.ai
MCP Server Supply Chain Security: The Install Path Nobody Reviews
A DeepInspect analysis lays out five review gates for securing the MCP server supply chain, arguing that adding a third-party MCP server grants code execution, credential access, and text injection with far less scrutiny than an npm dependency. It cites CSA/OX Security research finding 9 of 11 MCP marketplaces affected by a STDIO-interface design flaw, 40+ MCP CVEs in early 2026 (including CVE-2026-33032 in nginx-ui MCP and CVE-2026-0755 in gemini-mcp-tool, both CVSS 9.8), and details tool-description poisoning as indirect prompt injection (MITRE ATLAS AML.T0051.001). Details →First reported keycard.ai
The Agent Security Stack: Transport, Identity, Policy, Runtime
A Keycard explainer maps the "agent security stack" into distinct layers — transport (MCP/OAuth 2.1 authorization), identity, policy, and runtime guardrails that watch for prompt injection — arguing that agent security cannot be collapsed into a single control surface. The piece frames how multi-agent call chains multiply control surfaces (LLM tool invocation, transport, credential, authorization) and argues identity/authorization is the most under-served layer, citing recent CrowdStrike/SGNL and Palo Alto/CyberArk acquisitions. Details →First reported simspace.com
Exposing AI Agent Failure Modes Through Structured Cyber Exercises
SimSpace's blog post argues for using structured cyber exercises — combining red teaming, tabletop decisions, and automated simulations — to expose AI agent failure modes such as goal drift, tool misuse, context loss, and cascading logical errors before agents are deployed at scale. The piece lays out a failure-mode taxonomy (security vs. safety failures) and a five-phase validation flow, citing practitioner evidence that only 37% of a single-agent pipeline's outputs were error-free. Details →First reported asana.com
Breaking the Lethal Trifecta: How Asana Thinks About Agentic AI Security • Asana
Asana engineering explains how it approaches agentic AI security using Simon Willison's "lethal trifecta" framework — the convergence of access to sensitive data, exposure to untrusted content, and the ability to externally communicate (create side effects) that together enable prompt-injection attacks. The piece argues that since prompt injection cannot be reliably solved, defenders should break at least one leg of the trifecta, citing demonstrated attacks against Microsoft 365 Copilot (EchoLeak), GitHub's MCP server, and Slack AI. Details →First reported barndoor.ai
MCP Gateway Requirements for Enterprise Security Teams
Barndoor's blog outlines security requirements for enterprise MCP (Model Context Protocol) gateways, arguing that most MCP deployments lack access controls and identifying five gaps: all-or-nothing tool permissions, no user scoping, silent vendor-side changes, fragmented policy across AI clients, and unfiltered sensitive data. It recommends per-tool policy enforcement, IdP-driven identity, change management, and a default-deny posture. Details →First reported medium.com
The Last Patch. The MCP Attack Surface We’re Building… | by Zac | Jul, 2026
An opinion piece by Zac on Medium argues that the rush to expose MCP endpoints and build agent-to-agent (A2A) orchestration is creating a large new attack surface, where every MCP endpoint is an agent-callable function and every A2A handoff is a traversable trust boundary. The article draws on Anthropic's report mapping 832 accounts banned for malicious cyber activity (March 2025–March 2026) against MITRE ATT&CK, noting medium-or-higher-risk actors rose from 33% to 56% and that AI is increasingly used deeper in the attack lifecycle. Details →First reported medium.com
Prompt Injection Is Just SSRF for Text | MCP Security → Part 3 | by Abhishek meena | Jul, 2026
Part 3 of an MCP bug bounty guide by Abhishek meena frames MCP prompt injection as analogous to SSRF: tool outputs (URLs, files, emails, API responses) are attacker-controlled text that the model reads and treats as instructions. The write-up explains how to find, exploit, and argue indirect prompt injection via tool output, with sanitized PoCs referenced. Details →First reported traefik.io
MCP Gateway Best Practices | Traefik Hub Documentation
Traefik Hub documentation outlines security best practices for deploying an MCP Gateway in production, covering On-Behalf-Of (OBO) token delegation per RFC 8693, Task-Based Access Control (TBAC) for AI agents, and a defense-in-depth 'Triple Gate' pattern. The guidance emphasizes least-privilege access so that a compromised MCP server does not grant an attacker access to all backend resources. Details →First reported embracethered.com
Autonomous AI Intrusions Are Here: Lessons from the Hugging Face Compromise
An embracethered.com analysis examines two reported autonomous-AI intrusions: a Hugging Face compromise that Hugging Face says was driven end-to-end by an autonomous AI agent (entering via a malicious dataset and code-execution paths in its processing pipeline, then harvesting cloud/cluster credentials and moving laterally across 17,000+ recorded actions), and Sysdig's JADEPUFFER agent-driven ransomware that autonomously enumerated services, exploited Nacos auth bypass (CVE-2021-29441), forged JWTs, and self-corrected failed payloads to insert a backdoor admin. The write-up highlights a defensive asymmetry in which commercial-model safety guardrails blocked Hugging Face's own forensic analysis, forcing a pivot to a locally hosted open-weight model, and criticizes the lack of shared IOCs. Details →First reported medium.com
Prompt Injection Is No Longer Just a Chatbot Problem
A Medium explainer titled "Prompt Injection Is No Longer Just a Chatbot Problem" argues that as AI applications gain the ability to search documents, retain memory, call APIs, and run autonomous agent workflows, prompt injection now extends beyond chatbots to poison retrieved knowledge, corrupt long-term memory, manipulate an agent's plan, or trigger unauthorized tool calls. The piece frames prompt injection as a core security challenge across prompts, RAG, tools, memory, and agents. Details →First reported · updated · 4 reports sentia.community
The Confused Deputy with a Chat Window: Why AI Agents Are Exposing the Security Checks Enterprises Never Wrote – The Sentia AI Community
An explainer from the Sentia AI Community argues that autonomous, write-enabled LLM agents connected to production APIs re-introduce the classic 'confused deputy' problem: because an agent's interface is natural language, it lacks a native, cryptographic way to verify who authorized a given instruction, so untrusted input can drive privileged actions. The piece frames this as a structural gap in enterprise security models built around implicit human judgment and static perimeter API controls. Details →First reported · updated · 3 reports medium.com
Your AI Agent Trusts Every Tool It's Ever Been Introduced To
An analysis piece, 'The MCP paradox,' argues that the Model Context Protocol standardized not only how agents reach tools but also how attackers reach agents, walking through concrete vectors like tool poisoning attacks where a malicious tool description instructs an agent to exfiltrate secrets (e.g. SSH keys) via text the user never sees. The article cites Invariant Labs' April 2025 tool-poisoning proof of concept and MCP's own design choices, and proposes defensive controls to harden MCP servers. Details →First reported exein.io
Physical AI Security: A Threat Model for Edge Devices
Exein's blog post "Physical AI Security: A Threat Model for Edge Devices" argues that on-device AI (cameras, robots, drones running vision-language models and LLMs locally) introduces risks classic embedded threat models miss: every sensor becomes an instruction channel enabling physical-world prompt injection (e.g. text on a sign in front of a camera), probabilistic behavior that cannot be patched like a CVE, and unattended failures that act on the physical world via actuators. It proposes modeling the agent loop rather than individual components. Details →First reported · updated · 2 reports senthex.com
Prompt Injection Prevention for Coding Agents | Fiddler AI Blog
A Fiddler AI blog post explains prompt injection risks specific to coding agents, where untrusted inbound context (repositories, issues, docs, and tool returns) can turn an injected instruction into executed code or remote code execution. It argues model-level guardrails are bypassable and advocates layered prevention: isolating untrusted input, least-privilege tool and credential scoping, blast-radius containment, and runtime policy enforcement with decision lineage. Details →First reported · updated · 4 reports reversinglabs.com
MCP Supply Chain Attacks: Why Better Models Make It Worse
A dope.security blog post argues that the Model Context Protocol (MCP) has become a new shadow-IT and supply-chain risk because MCP servers create outbound HTTPS connections that read files, hit APIs, and move data on an agent's behalf while looking indistinguishable from ordinary encrypted traffic. It contends DNS filters and cloud proxies cannot see the URL paths, payloads, or tool calls inside MCP sessions, and promotes the vendor's device-level SWG and DLP as a means to name, allow, or block MCP servers at egress. Details →First reported clawsecure.ai
AI Agent Security: The Complete 2026 Guide
ClawSecure's blog post is a 2026 explainer guide on AI agent security, describing why autonomous agents break traditional security (broad access, autonomy, and treating data as instructions) and cataloging risks like prompt injection, tool poisoning, credential theft, and data exfiltration mapped to the OWASP Top 10 for Agentic Applications. It cites ClawSecure's finding that 41% of popular OpenClaw skills carry security vulnerabilities and promotes the company's runtime monitoring and integrity-layer product. Details →First reported · updated · 6 reports darktrace.com
Securing AI with a Defense-in-depth Strategy
Darktrace's blog by Nicole Carignan argues that securing AI requires a defense-in-depth strategy spanning governance, identity, data security, secure development, runtime monitoring, and incident response, rather than relying solely on model guardrails or prompt filtering. It draws on the upcoming NIST Cybersecurity Framework Profile for AI and Five Eyes guidance on careful adoption of agentic AI services. Details →First reported google.com
Mitigate indirect prompt injection risks from Google Cloud MCP | Google Cloud Data Agent Kit extension for Antigravity IDE | Google Cloud Documentation
Google Cloud documentation for the Data Agent Kit extension in the Antigravity IDE describes indirect prompt injection risks from Google Cloud MCP, where locally deployed coding agents running with a user's full privileges can misinterpret attacker-planted data (e.g., in email, calendar, Cloud Storage, or BigQuery) as instructions. The guidance recommends guardrails such as running agents in constrained environments to reduce risk to infrastructure and data. Details →First reported securiti.ai
What Anthropic’s Zero Trust for AI Agents Means for the Data Layer
Securiti's blog post interprets Anthropic's zero-trust guidance for AI agents and argues that the data layer is the highest-leverage control point for securing and governing agentic AI. The piece is vendor thought-leadership tying the zero-trust-for-agents concept to Securiti and Veeam's data-governance and 'Agent Commander' offerings. Details →First reported medium.com
Why Your MCP Server Fails Its First Security Review: 14 Gaps and a Scorecard (TypeScript Edition) | by Rick Hightower | Jun, 2026 | Spillwave Solutions
Rick Hightower's article presents a TypeScript-focused security-review checklist for Model Context Protocol (MCP) servers, enumerating 14 production gaps including shared API keys, missing audit logs, prompt-only guardrails, prompt injection through tool results, weak tenant isolation, non-idempotent mutations, schema drift, unmanaged secrets, and missing DLP, plus a maturity scorecard. It offers code patterns to close the most dangerous gaps and hardening guidance for moving MCP servers from demo to production. Details →First reported · updated · 2 reports cloudsecurityalliance.org
MCP Security in the Cloud: Where the Real Risks Begin
A Darktrace/CSA analysis (drawing on the arXiv paper 'Securing the Model Context Protocol (MCP): Risks, Controls, and Governance') outlines seven MCP security risks CISOs should prepare for, including content-injection/prompt-injection attacks, over-privileged agents, tool poisoning, supply-chain compromise via malicious MCP servers, and data exfiltration. It notes MCP handles only connection mechanics without built-in identity or access controls, amplifying the 'lethal trifecta' of sensitive-data access, untrusted content exposure, and external communication. Details →First reported howtoharden.com
Cursor Hardening Guide
The Cursor Hardening Guide from howtoharden.com compiles defensive controls for the Cursor AI code editor, covering AI privacy settings, MCP server security, agent sandboxing, API key management, rules-file integrity, and extension supply-chain risk. It draws on 2025-2026 CVE analysis (including CurXecute RCE via MCP prompt injection CVE-2025-54135, MCPoison persistent compromise CVE-2025-54136, and sandbox/file-overwrite bugs) and ships runnable config packs mapped to OWASP LLM/Agentic Top 10, NIST AI RMF, and MITRE ATLAS. Details →First reported snyk.io
Cursor’s AI Security Agents: What They Get Right (and What’s Missing)
Snyk analyzes Cursor's four autonomous AI security agents, which review 3,000+ PRs weekly and catch 200+ vulnerabilities using a short prompt sitting atop a production-grade agent orchestration platform (custom MCP server, webhook orchestration, state management). The piece praises the engineering while arguing there is a meaningful gap between LLM agents reviewing PRs and a full enterprise security program. Details →First reported powerdmarc.com
Malicious MCP Servers & Email Security: The New Supply Chain Threat
The article analyzes the postmark-mcp incident, where a malicious actor published an exact-name lookalike npm package impersonating Postmark's official Model Context Protocol (MCP) server. Across 15 clean releases it built trust before adding a hidden BCC rule that silently forwarded 3,000-15,000 corporate emails per day to an attacker-controlled domain, leaking passwords, invoices, customer data, and auth tokens; because mail flowed through legitimate infrastructure, SPF and DKIM passed automatically. Details →First reported detect.fyi
Detection Engineering in the Era of Semantic Malware | by Koifsec | Jul, 2026
A detection-engineering analysis examines "semantic malware" / "promptware" — malware delivered through prompt injection rather than binaries — using Origin's Brainworm PoC (a poisoned CLAUDE.md file that hijacks AI coding assistants into registering with a C2 server over RabbitMQ) and the Ben-Gurion/Tel Aviv/Harvard/Toronto "Promptware Kill Chain" arXiv paper as anchors. The kill chain formalizes seven stages (initial access via prompt injection, jailbreaking, reconnaissance, memory/retrieval poisoning, command-and-control, lateral movement, actions on objective) across 36 documented incidents, and the piece discusses how defenders can detect such trust-boundary failures. Details →First reported vaibot.io
Prompt injection is an egress problem
A VAIBot blog post reframes prompt injection as an egress problem, arguing that input-side detection of injected instructions is unwinnable and that defenders should instead gate the actions an agent can take (commands, network calls, tool invocations) with allow/approve/deny policies and tamper-evident receipts. The post promotes VAIBot's 'guard' npm package and MCP server as the enforcement point for this approach. Details →First reported thehackernews.com
What Changes When Your Software Supply Chain Includes AI Writing Your Code?
An analysis/webinar-tied piece from The Hacker News arguing that AI-assisted coding and agentic tooling (via MCP, autonomous package-pulling agents, and prompts as build inputs) have expanded the software supply chain attack surface beyond traditional dependency risk. It references prior incidents (SolarWinds, Log4Shell, XZ Utils, and the self-propagating Shai-Hulud package campaign) to frame why knowing what's in your code is no longer sufficient. Details →First reported akamai.com
The New MCP Specification: What Security Teams Must Prepare For
Akamai analyzes the upcoming MCP 2026-07-28 specification, which moves the Model Context Protocol to a stateless, enterprise-grade architecture with application-managed state, rich interactive UI apps, and long-running async tasks. It argues that while the update eliminates historical risks like protocol-level session hijacking and weak auth, it shifts security boundary responsibility to developers and opens new abuse avenues: unauthorized customer-data access, phishing through trusted AI interfaces, bypass of enterprise controls, and service disruption via background-processing abuse. Details →First reported agentsafelabs.com
Prompt Injection Is Not a Chatbot Problem: How the Attack Surface Changes When Your LLM Has Tools
An explainer arguing that chatbot-era prompt injection defenses (input filtering, output monitoring, instruction hierarchy, adversarial training) fail against agentic systems because injection enters through tools, retrieved documents, memory, API responses, and inter-agent instructions rather than the user message. It frames the issue as a system-architecture and trust-boundary problem rather than a model-tuning one. Details →First reported nvidia.com
How to Govern Autonomous Agents in Enterprise AI Factories
An NVIDIA technical blog describing the Secure Agent Workspace Reference Design, which separates the presentation layer (user device) from the execution layer (a managed, sandboxed workspace) to govern autonomous AI agents. It recommends per-user managed VMs, SSO enforcement, network egress controls, human approval for significant actions, credential protection via proxies, signed security policies, and centralized logging/audit. Details →First reported adversa.ai
OWASP ASI03: Identity & Privilege Abuse in AI Agents
A technical guide on OWASP's ASI03 (Identity & Privilege Abuse in AI Agents), covering five identity abuse vectors, the Salesloft Drift breach case study, the attack lifecycle, and detection/prevention with task-scoped, time-bound access. Details →First reported stackoverflow.blog
AI agents are a confused deputy with the keys to your kingdom
A Stack Overflow analysis frames LLM agents as inherent 'confused deputies' that wield real privileges on behalf of less-privileged requesters, using a described Meta AI support-assistant account-takeover to illustrate how agents carry out permitted operations without verifying who is authorized. It argues agents cannot reliably separate instructions from data, making indirect prompt injection via ingested content the dominant class of agent attack. Details →First reported stackbuilders.com
Stack Builders - When Text Becomes Code: Securing LLM–Database Integrations
A technical guide based on a Quito Lambda talk demonstrating how prompt injection (direct, indirect, and confused-deputy/exfiltration) can compromise LLM applications that generate SQL over a live Postgres database, using an example LLM-powered SQL analyst with a Streamlit frontend. It walks through layered defenses and what they stop or fail to stop. Details →First reported arcis-website.pages.dev
Inside MCP: defending the runtime layer of agent security · Arcis Blog
An Arcis blog post argues that agent security has four layers (identity, pre-deploy testing, observability, runtime defense) and that the runtime hot path is structurally underserved. It frames MCP's explicit tool-call contract as enabling runtime defense against agent toolcall injection (their vector V32), applying allowlist/sanitize/refuse techniques at the agent-tool boundary. 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