wk-sharpen
Warn
Audited by Snyk on Aug 19, 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). In wk-sharpen’s batch mode, the agent scans user-authored learning/retro text from the repo directories
learnings/skills/andlearnings/retrospect/and distills the contents, so outsider-submitted poison can be ingested via posted files.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata