google-maps-reviews
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze customer reviews for local businesses on Google Maps. Since these reviews are external, untrusted content provided by third parties, they could contain malicious instructions (indirect prompt injections) intended to influence the agent's behavior or exfiltrate data from the current session.
- Ingestion points: Customer reviews fetched via the
google_maps_bulk_reviewstool. - Boundary markers: None specified; the skill does not explicitly instruct the agent to treat review content as untrusted or use delimiters.
- Capability inventory: The agent uses
sandbase_call_toolto interact with external services. - Sanitization: No sanitization or filtering logic is described for the retrieved review data.
- [NO_CODE]: The skill consists entirely of Markdown instructions and documentation. There are no Python scripts, Node.js files, or other executable binaries provided within the skill package, which reduces the direct attack surface for traditional code-based exploits.
Audit Metadata