to-tasks
Warn
Audited by Snyk on Jul 23, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). The runtime workflow explicitly instructs reading “any supplied file, issue, URL or wiki article” (outsider-authored free text via user-provided URLs/issues/wiki bodies) into the agent’s context during “Gather context” step 1.2.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata