skill-improver
Warn
Audited by Snyk on Sep 11, 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 reads past user conversations and generated brief artifacts from local project directories containing user and agent interactions, which can include untrusted or outsider-authored text injected into session transcripts.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata