» Tag
llm-security
16 postsStudy: LLMs have a fundamental role-recognition flaw hackers can exploit
Researchers show LLMs identify roles by text style, not tags, revealing a fundamental flaw that may make full LLM security unattainable.
The Lethal Trifecta Hiding in Your MCP Server, and How to Defuse It
An exploit-free attack on GitHub's MCP server reveals the 'lethal trifecta' risk in agent tooling, and the architectural fix engineers need.
Everyone Hopes AI Fails, I'm Building the Net Anyway
AI agents deleted production databases due to access-versus-authorization confusion; the author now tests a safety net combining AI proposals with code checks.
CommitBrief — AI code reviews, right in your terminal
A provider-agnostic, local-first CLI that reviews your staged changes, a historic range, or a whole GitHub pull request. Zero telemetry, no server. Free and open source.
commitbrief.comBioinformatics meets prompt injection defense: the Smith-Waterman trick
An open-source technique adapts the 1981 Smith-Waterman DNA alignment algorithm to catch paraphrased prompt injections that regex and classifiers miss, boosting F1 by 34 points.
AI Agent Security Decisions Belong at the Tool Call
Real security for AI agents lies not in setting up MCP connections but in runtime control of each tool call; the HCP paper shows why with concrete evidence.
Makoto Blocks False Claims by Claude Code AI Agents
Makoto is an integrity hook for Claude Code that checks agent claims like passed tests or commits against real tool-call logs and blocks mismatches.