semgrep-rule-creator

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

• Third-party content exposure detected (low risk: 0.10). The agent skill instructs the LLM to fetch and ingest multiple remote Semgrep documentation markdown files via WebFetch before writing rules.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill documentation references 7 raw GitHub URLs for external Semgrep and Trail of Bits documentation that are fetched via WebFetch and used as operational instructions/guidelines, and these third-party repository URLs lack explicit strong provenance (first-party cryptographic attestation or verified immutable references), evaluating to high.