gps-mcp

Pass

Audited by Gen Agent Trust Hub on Jul 31, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted external data from the Google Play Store, creating a surface for indirect prompt injection (Category 8).
  • Ingestion points: The gps_list_reviews tool (referenced in SKILL.md) reads user-generated content into the agent's context.
  • Boundary markers: The instructions do not define specific delimiters or "ignore instructions" wrappers for the interpolated content.
  • Capability inventory: The skill enables management actions on the Google Play Store, including potentially destructive write operations.
  • Sanitization: Agent Rule 3 requires the agent to confirm destructive actions with the user, providing a human-in-the-loop safety mechanism against malicious injected instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 31, 2026, 02:45 PM
Security Audit — agent-trust-hub — gps-mcp