llvm-learning

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

• Third-party content exposure detected (low risk: 0.10). The workflow fetches an external README from a GitHub repository (awesome-llvm-security) at runtime, which exposes the agent to outsider-authored free text.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs the agent to fetch external content from an arbitrary repository raw URL (https://raw.githubusercontent.com/gmh5225/awesome-llvm-security/refs/heads/main/README.md) for resource links and tutorials, introducing an unverifiable runtime external dependency.