external-context
Warn
Audited by Snyk on Mar 20, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The SKILL.md Step 2 Task invocation explicitly instructs spawned document-specialist agents to "Use WebSearch and WebFetch" to retrieve content from official docs, GitHub, blogs, etc., so the agent will fetch and interpret untrusted third-party web content (URLs) that can influence its outputs.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata