config-export
Warn
Audited by Snyk on Aug 14, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). SKILL.md Step 1 “Read and bundle source files” ingests user/outsider-authored free text from the current project’s
CLAUDE.mdandai-context/*.md(Step 1 collects them into the in-context bundle for LLM transformation) before generating Copilot/Gemini/Cursor instruction files.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata