ev-charger-nearby

Pass

Audited by Gen Agent Trust Hub on Aug 1, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches data from k-skill-proxy.nomadamas.org (vendor infrastructure) or apis.data.go.kr (official South Korean government API portal). These are legitimate, purpose-specific endpoints for retrieving EV charging station data.
  • [COMMAND_EXECUTION]: The skill uses urllib for network requests and argparse for CLI management. It does not spawn subprocesses or execute system commands. Dynamic module loading in the test suite (importlib.util) is restricted to the skill's own local script for unit testing purposes.
  • [CREDENTIALS_UNSAFE]: The skill follows security best practices by resolving API keys from environment variables or a local .env file at a standard configuration path (~/.config/k-skill/secrets.env). It explicitly redacts these keys during --dry-run operations to prevent accidental exposure.
  • [DATA_EXFILTRATION]: No sensitive local data is accessed. The skill only transmits user-provided search parameters (location, station IDs) to the designated API endpoints to fulfill the user's request.
  • [PROMPT_INJECTION]: The skill instructions (SKILL.md) are strictly functional and do not contain patterns designed to override agent behavior or bypass safety guardrails.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 1, 2026, 01:46 PM
Security Audit — agent-trust-hub — ev-charger-nearby