best-practices-audit
Warn
Audited by Snyk on Jun 22, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.65). The skill’s runtime reads outsider-authored project files (e.g., it uses the Read tool to ingest the repository’s
CLAUDE.mdand a reference file under.claude/skills/...), and that readable Markdown can contain arbitrary free text from parties other than the operating user.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata