evidence-add
Warn
Audited by Snyk on Jun 19, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The required workflow (“evidence-add”) ingests a
snippetthat is verbatim text from a providedsource(URL/identifier) at runtime, which—when that source is public web content or other outsider-authored text—becomes LLM-readable free text via the tool input.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata