prompt-engineering-refine
Warn
Audited by Snyk on Aug 25, 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 runtime workflow described in SKILL.md (“Write → Test → Analyze → Improve”) uses a user-provided prompt/fixture set as inputs for evaluation, meaning outsider-authored free text can be ingested into the agent’s test loop without selecting a specific item first.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata