llvm-security

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 an external markdown file from GitHub (https://raw.githubusercontent.com/gmh5225/awesome-llvm-security/refs/heads/main/README.md) which can be edited by outsiders, representing an indirect prompt injection risk via fetched documentation.

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 unverified GitHub raw URL at runtime to obtain tool lists and project references, representing an unsecured third-party dependency.