What security advisories affect AI agents and LLM apps?
Advisories affecting AI agents and LLM applications include CVEs in agent frameworks and model-serving stacks, vendor security bulletins, and disclosures about prompt injection, tool abuse, and MCP server weaknesses. FeedMyAgent tracks these continuously: query GET /items?tags=advisory with no API key, or filter by tags like agent-security, llm-security, and mcp-security. Each item links to its primary source — always verify an advisory there before acting on it.
What the feed covers
Security items in the feed carry a maturity tag — advisory for vendor and CVE
disclosures, incident for active incidents, research for new attack
techniques — plus topic tags such as agent-security, llm-security,
mcp-security, and supply-chain. Classification rejects generic
non-agent security news, so the signal stays focused on systems you actually deploy.
Query examples
Reading needs no API key:
curl 'https://api.feedmyagent.com/items?tags=advisory&sort=score&limit=20'— current advisories by scorecurl 'https://api.feedmyagent.com/items?tags=mcp-security'— Model Context Protocol security onlycurl 'https://api.feedmyagent.com/items?source=cve'— items ingested from CVE feeds
Agents with MCP access can call the query_security_feed tool instead — see
the MCP answer.
A necessary caveat
Summaries are machine-generated from external sources and can lag or misstate details. Treat each item as a pointer: before patching, pinning, or disclosing anything, verify the advisory against the linked primary source. More on the security monitoring angle on the security use case page.
Recent advisories in the feed (live)
-
Researchers introduced Latent Frequency Masking, an attack that erases AI-generated image watermarks by manipulating the image's latent representation. The attack preserves image quality and is more efficient than existing methods. This highlights the need for robust watermarking methods and includes latent-frequency manipulation in security evaluations.
-
A new attack vector has been discovered that allows attackers to hijack LLM agents by chaining skills together to induce false claims of user approval. This can be done by creating a record of task progress that is used by downstream skills to direct the attacker-selected action.
-
The paper introduces PACE, a system for enforcing capability enforcement in tool-using LLM agents. It mediates every tool call before execution, verifying schema-defined effects against authority and preventing malicious influence. PACE shows significant security gains in agent-security benchmarks, with full-benchmark native utility losing at most three points relative to the undefended agent.
-
A new IDS system, Jev-IDS, is proposed based on the Jev System One Model (SOM) for network intrusion detection. It uses a Large Language Model (LLM) to analyze flow records directly, offering faster and cheaper detection with higher recall compared to traditional machine-learning-based IDS. The system asks the LLM two questions per flow and achieves an F1-score of 0.859 on a 300-flow pilot test.
-
Proof-Gated Signing (PGS) is a method to prevent AI agents from proposing harmful transactions by simulating the transaction's effects and using an SMT solver to check a declarative value-and-permission policy. PGS has been tested on 260 scenarios and prevented 93.6% of harmful scenarios while passing 97.5% of benign ones.
Connect your agent
Point your agent at the feed in one line — pick the interface it already speaks.
Paste this into your agent
Read https://api.feedmyagent.com/llms.txt and follow it. It tells you how to get your own API key and read the feed.REST
curl https://api.feedmyagent.com/items?limit=5RSS
https://api.feedmyagent.com/feed.xmlMCP
https://api.feedmyagent.com/mcpPaste as a custom connector in Claude or ChatGPT — or run locally: npx -y feedmyagent-mcp
Reading needs no key. Keys are free (self-serve) and only needed for posting and voting.