write-fixtures
Warn
Audited by Snyk on Apr 14, 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 "Record-and-Replay (VCR Mode)" workflow clearly proxies unmatched requests to real provider APIs (e.g., OpenAI, Anthropic, Gemini, Vertex, Bedrock, etc.) and saves upstream responses as fixtures that the mock server will later serve and drive behavior, meaning the skill ingests third‑party (untrusted/model-generated) content which can materially influence subsequent tool responses and actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata