docs-researcher
Warn
Audited by Snyk on Mar 24, 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 research process (step "2. Fetch Documentation") explicitly instructs the agent to use WebFetch and WebSearch to retrieve documentation from listed public sites (e.g., tailwindcss.com, guides.rubyonrails.org, other libraries), meaning the agent will fetch and read open third-party web content that could contain untrusted, user-provided instructions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata