goplaces

Pass

Audited by Gen Agent Trust Hub on Jul 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes the goplaces command-line utility to perform location searches, resolve place names, and fetch place details or reviews.
  • [EXTERNAL_DOWNLOADS]: The skill installs the goplaces tool from the Homebrew tap steipete/tap/goplaces.
  • [PROMPT_INJECTION]: The skill processes untrusted external data retrieved from the Google Places API, such as user-generated reviews and place descriptions, which introduces an indirect prompt injection surface.
  • Ingestion points: Untrusted data enters the agent context through the output of goplaces search, details, and reviews commands.
  • Boundary markers: None. The skill does not define specific delimiters or instructions for the agent to ignore potentially malicious instructions embedded in the API responses.
  • Capability inventory: The skill is capable of executing the goplaces CLI tool.
  • Sanitization: There is no evidence of filtering, escaping, or validation of the content returned by the Google Places API before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 16, 2026, 09:13 PM
Security Audit — agent-trust-hub — goplaces