orchestrator
Warn
Audited by Snyk on Mar 24, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The Plan Workflow (section 3.1 "Source Types") explicitly instructs the agent to fetch and ingest user-generated content from external sources—e.g., "gh issue view --json body,comments", "gh pr view --json body,comments", and "Jira API"—which the orchestrator must read and use to form plans and dispatch workers, allowing untrusted third-party text to influence behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata