ergonomics
Warn
Audited by Snyk on Oct 21, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The skill instructs the agent to read help pages, tool outputs, error messages, and CLI/API responses during live exercise or plan mode, which can contain outsider-authored text when evaluating external tools or APIs.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata