korean-transit-route

Pass

Audited by Gen Agent Trust Hub on Oct 22, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill instructs the agent to execute npx -y @nomadamas/k-skill@0, which downloads and runs a package from the npm registry to provide dynamic instructions and updates. This is a vendor-specific deployment pattern.
  • [EXTERNAL_DOWNLOADS]: The skill fetches transit data from api.odsay.com and utilizes a geocoding proxy at k-skill-proxy.nomadamas.org. These domains are either official service endpoints or vendor-managed infrastructure.
  • [COMMAND_EXECUTION]: The instructions include bash snippets for loading environment variables from ~/.config/k-skill/secrets.env and performing API calls via curl. It also uses python3 -c for URL encoding within the shell.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied location strings and address data retrieved from a proxy. While this presents an attack surface for indirect prompt injection, the skill uses standard URL encoding (urllib.parse.quote) and clear data schemas to handle external content.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 22, 2026, 09:12 PM