google-maps-api
Pass
Audited by Gen Agent Trust Hub on Nov 13, 2026
Risk Level: SAFEDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The skill performs network operations to
api.scavio.dev. These endpoints are vendor-owned resources associated with the skill author, scavio-ai, and are necessary for the skill's primary function. - [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes data from external sources (Google Maps business listings and user reviews) which could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: Data returned from the
/maps/search,/maps/place, and/maps/reviewsendpoints as described inSKILL.md. - Boundary markers: Absent; there are no specific instructions or delimiters provided to separate external data from system instructions.
- Capability inventory: The skill utilizes
requests.postto interact with external APIs. - Sanitization: Absent; while the skill advises agents to only return API data and not to fabricate info, it provides no mechanisms for escaping or filtering malicious content within the external data strings.
Audit Metadata