skills/firecrawl/openclaw/goplaces/Gen Agent Trust Hub

goplaces

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill is designed to execute the goplaces binary to perform text searches, resolve place names, and fetch place details. All primary functionalities rely on local command execution.
  • [EXTERNAL_DOWNLOADS]: The skill documentation and metadata specify installation of the goplaces tool from a third-party Homebrew tap (steipete/tap/goplaces). While Homebrew is a standard package manager, the binary originates from a personal repository rather than a verified organization.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a vulnerability surface where untrusted user input (e.g., search queries, place names, or place IDs) is interpolated into command-line arguments.
  • Ingestion points: User-supplied strings in goplaces search, goplaces resolve, and goplaces details commands.
  • Boundary markers: None present in the skill instructions to delimit user input from shell commands.
  • Capability inventory: Execution of a third-party binary (goplaces) with network access to the Google Places API.
  • Sanitization: No specific sanitization or escaping logic is defined within the skill instructions for the user-supplied arguments.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 07:53 PM
Security Audit — agent-trust-hub — goplaces