docs-search
Warn
Audited by Snyk on Jul 6, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). High likelihood: the required workflow includes runtime WebFetch/scraping of a library’s public docs (and fallbacks to GitHub issues/Discord/forum), which are outsider-authored free text that can be injected into the agent’s LLM context.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.80). The skill explicitly instructs probing /llms.txt (e.g., https://anthropic.com/llms.txt, https://effect.website/llms.txt, https://tailwindcss.com/llms.txt) at runtime and to treat its fetched contents as the AI-canonical navigation source, so remote llms.txt (and similar runtime-fetched doc/changelog/samples URLs such as https://stripe.com/docs, https://stripe.com/changelog, https://github.com/stripe-samples) directly control agent navigation/prompts.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata