This week in the Wild West Roundup.
- This week in the Wild West Roundup.
- "Microsoft Threat Intelligence discovered that Anthropic's Claude Code GitHub Action could expose CI/CD workflow secrets when AI agents process untrusted GitHub content, including issue bodies, pull request descriptions, and comments.
- We found that while Claude Code Action supported environment scrubbing for subprocess execution paths such as Bash, the Read tool was not subject to the same sandboxing model.
- It was eventually authorized to access /proc/self/environ, reading the workflow's ANTHROPIC_API_KEY and potentially other credentials available to the runner."
- Another new attack: Phishing for Lobsters: How We Tricked OpenClaw into Spilling Secrets.
- Yet another new attack: Compromise OpenClaw with Prompt Injections in Message Objects.
- Brave browser discovers that no agentic browser has solved this problem.
- A new technique: dangerous worms say forbidden things so the LLMs in security scanners will stop scanning them.
- "Why AI agents introduce a new security model"
- "Chrome's WebMCP guidance warns that AI agents can be manipulated through the tools they are built to trust."