grounding-lite
Warn
Audited by Snyk on Mar 24, 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). This skill calls the Google Maps MCP at mapstools.googleapis.com and returns AI summaries and Google Maps links (public, potentially user-generated content) that the agent is expected to read and use to inform search, weather, and routing decisions, allowing third-party content to influence behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata