openai-api
Warn
Audited by Snyk on Mar 10, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md Vision section (e.g., the "Image via URL" examples) and related templates instruct the agent to ingest images from arbitrary external URLs, which are untrusted third‑party content the model will read and that can materially influence its responses.
Audit Metadata