yao-websecurity-skill
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 required workflow (SKILL.md step 2 and the README quick-use example using python3 scripts/security_audit_report.py prepare-env --source "" including GitHub URLs) explicitly instructs the agent to clone/fetch GitHub repos or staging URLs and then read and triage that code, meaning it ingests untrusted, user-generated third‑party content that can materially influence analysis and subsequent actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata