geo-technical
Warn
Audited by Snyk on Aug 12, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The skill instructs fetching attacker-influenced arbitrary target URLs at runtime (e.g., collecting a target URL and using curl/WebFetch to retrieve raw HTML and HTTP headers), so outsider-authored page content can be ingested into the LLM’s processing pipeline.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata