google-maps-api

Pass

Audited by Gen Agent Trust Hub on Sep 3, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill interacts exclusively with the vendor's official API domain (api.scavio.dev). All documentation and support links point to the vendor's primary website (scavio.dev and scavio.tech).
  • [SAFE]: The skill demonstrates secure credential handling by instructing users to load the SCAVIO_API_KEY from environment variables or secret stores, explicitly advising against hardcoding them in source control.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources (Google Maps reviews and place information). While this presents a theoretical attack surface, the risk is mitigated by the skill's instructions to return only structured API data and the agent's internal guardrails.
  • Ingestion points: Data enters the context via local_results[], place_results, and reviews[] fields from the api.scavio.dev responses in SKILL.md.
  • Boundary markers: The skill uses structured JSON responses which helps delineate data from instructions.
  • Capability inventory: The skill uses standard network requests (POST) to a specific vendor endpoint. No arbitrary command execution or file system writes are present.
  • Sanitization: The instructions explicitly state 'Never fabricate place names, ratings, addresses, or review text. Only return API data,' which discourages the agent from interpreting data as instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 3, 2026, 12:23 PM
Security Audit — agent-trust-hub — google-maps-api