llvm-tooling

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (low risk: 0.10). The required workflow fetches and ingests an external README from a GitHub repository via https://raw.githubusercontent.com/gmh5225/awesome-llvm-security/refs/heads/main/README.md, which exposes the agent to outsider-authored free text via low-privilege community list content.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs fetching external content from an arbitrary GitHub repository at runtime for tool lists and project references, representing an unverified external operational dependency.