Office Party: a planted file in /tmp runs code through Anthropic's Office skills on Linux
AIR Security says Anthropic's docx, pptx and xlsx skills load a LibreOffice shim from a fixed temp path without checks. Anthropic calls it out of scope.
Topic · 6 stories
6 stories tagged agent-skills on AI Tamer, newest first.
AIR Security says Anthropic's docx, pptx and xlsx skills load a LibreOffice shim from a fixed temp path without checks. Anthropic calls it out of scope.
SkillSpector checks Claude Code, Codex and MCP skills for injection, exfiltration and supply-chain risk, then scores them 0 to 100. How to run it.
Rig's terminal agent now installs with cargo install rig. 0.46.0 adds opt-in MCP, ACP for editors, AGENTS.md, skills and traffic logs.
Devin Vulnerability Fixes is an MIT set of SKILL.md skills: inventory, an approval gate, verified versions, tests in the new image, one PR per repo.
Anthropic, OpenAI, Hugging Face and Alibaba gave four agent projects to the Linux Foundation's agent group, which now hosts 10 projects including MCP.
In 90 of 6,637 malicious agent skills, VirusTotal found the payload hidden where reviewers don't see it but agents still read it. Here is how to check.