skill-auditor
Warn
Audited by Snyk on May 18, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill includes a remote-scanning feature that fetches arbitrary public GitHub repositories via scripts/scan-url.js (and then runs analyzers including the LLM semantic analyzer) so untrusted, user-generated code from GitHub is ingested and used to drive severity adjustments and CI actions (e.g., --use-llm and --fail-on-findings), allowing third-party content to materially influence decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata