claude-api
Warn
Audited by Snyk on Mar 23, 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 explicitly instructs the agent to use WebFetch/WebSearch (see python/agent-sdk/README.md built-in tools and the "When to Use WebFetch" plus shared/live-sources.md which lists live public URLs like platform.claude.com and GitHub) so the agent will fetch and interpret open/public third‑party web content that can change model/tool selection and subsequent actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata