google-maps
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [Prompt Injection] (SAFE): No instructions designed to override agent behavior or bypass security protocols were identified.
- [Data Exposure & Exfiltration] (SAFE): No hardcoded credentials or sensitive data access patterns were found.
- [Obfuscation] (SAFE): No use of encoding or hidden characters to mask malicious intent was detected.
- [Unverifiable Dependencies & Remote Code Execution] (SAFE): No external dependencies are defined and no remote code is downloaded or executed.
- [Indirect Prompt Injection] (SAFE): 1. Ingestion points: 'query' and 'address' parameters in SKILL.md tools. 2. Boundary markers: Absent. 3. Capability inventory: Location search, directions, and geocoding tools only; no arbitrary code execution. 4. Sanitization: Absent in the high-level definition.
Audit Metadata