static-analysis

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

• Third-party content exposure detected (low risk: 0.10). The skill instructs the agent to fetch external markdown content from a GitHub raw URL, exposing it to outsider-authored free text via repository 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 URL (https://raw.githubusercontent.com/gmh5225/awesome-llvm-security/refs/heads/main/README.md) to obtain tool lists and resource references at runtime, representing a weak/unknown external dependency.