browse-geo
Warn
Audited by Snyk on Apr 14, 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.md explicitly instructs the agent to browse and extract content from public third-party search pages (Step 1: Google AI Overviews via camoufox goto "https://www.google.com/search..."; Step 2: Perplexity via "https://www.perplexity.ai/search..."; Step 3: ChatGPT Search via an authenticated profile) and to interpret those results (citations, contexts, competing domains) to drive visibility metrics and recommendations, which meets the criteria for ingesting untrusted third‑party content that can influence actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata