gtmetrix
Warn
Audited by Snyk on Apr 25, 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's SKILL.md instructs the agent to start tests and fetch detailed reports for arbitrary public URLs via Membrane's proxy to the GTmetrix API (see "Start Test", "Get Report", "List Page Reports" and the "membrane request" proxy examples), which means the agent will ingest and act on content derived from untrusted public webpages that could contain instructions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata