llvm-optimization

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

• Third-party content exposure detected (low risk: 0.10). The skill contains instructions to fetch and ingest a remote README from GitHub (https://raw.githubusercontent.com/gmh5225/awesome-llvm-security/refs/heads/main/README.md), which constitutes reading third-party/external 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 a raw GitHub URL (https://raw.githubusercontent.com/gmh5225/awesome-llvm-security/refs/heads/main/README.md) to obtain tool lists and project references, which represents an unverified runtime external dependency from an individual-owned repository.