gsd-review
Warn
Audited by Snyk on Jul 22, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.65). The required workflow invokes external AI CLIs (e.g., Gemini/Claude/Codex/OpenCode/Qwen/Cursor) and therefore will ingest their responses back into the agent’s context at runtime, which creates an indirect prompt-injection risk via outsider-authored free text returned by those third-party services.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata