learn-codebase
Warn
Audited by Snyk on Aug 7, 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). The workflow ingests outsider-authored free text at runtime by reading SKILL.md files found in user-accessible skill directories from disk (e.g.,
./skills,~/.agents/skills) viascripts/list_skills.py, parsing their frontmatter into the<available_skills>used for selection.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata