geo-review
Warn
Audited by Snyk on Apr 19, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill's required workflow (Phase 3 and the TEST category in SKILL.md) explicitly opens a browser session to navigate and scrape public sites (target URLs, /llms.txt, robots.txt, Perplexity, Google AI Overviews) and instructs the agent to extract and act on that third-party content to score and remediate the site, which allows untrusted web content to influence decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata