ai-chat
Warn
Audited by Snyk on May 3, 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 skill accepts arbitrary external content (e.g., image_url in the Vision example) and includes a "references" parameter in the Stateful Conversations section, so the agent may ingest untrusted third‑party content that could carry implicit instructions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata