geolocation-skill

Warn

Audited by Snyk on Feb 15, 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 "Web Search Verification" workflow (see SKILL.md and reference/verification-strategies.md) explicitly directs the agent to perform web searches and interpret results from open/public sources (Street View/Maps, local news, business sites, and other user-generated content) as part of verification, exposing it to untrusted third-party content that could carry indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 09:03 PM