google-maps-search-api-skill
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data retrieved from external Google Maps search results.
- Ingestion points:
scripts/google_maps_search_api.pyfetches and prints business names, addresses, and review snippets from external sources via the BrowserAct API. - Boundary markers: The skill instructions do not define boundary markers or provide specific guidance to the agent to disregard potential instructions embedded in the extracted data.
- Capability inventory: The skill executes a Python script (
scripts/google_maps_search_api.py) capable of performing network requests and outputting large amounts of data to the agent's context. - Sanitization: There is no evidence of sanitization or filtering of the extracted text content before it is passed to the AI agent.
- [COMMAND_EXECUTION]: The skill requires the agent to execute a Python script to perform search and polling operations.
- [EXTERNAL_DOWNLOADS]: The skill's Python script relies on the well-known
requestslibrary for communicating with the vendor's API endpoints atapi.browseract.com.
Audit Metadata