anthropic-api
Warn
Audited by Snyk on Mar 29, 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.md explicitly shows a "Vision (Image Analysis) — URL Image" example where messages include an image with source.type: 'url', demonstrating the agent can fetch and ingest arbitrary external URLs (untrusted third‑party content) and will interpret that content as part of its workflow.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata