skill-autobench
Warn
Audited by Snyk on Aug 13, 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 skill’s runtime workflow mines “Brain conversation archive” pages under
conversations/(populated by a prior archive skill) and scans per-harness session transcripts, which are outsider-authored free text submitted by end users in those chats/transcripts before generating the eval.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata