seoul-subway-arrival

Pass

Audited by Gen Agent Trust Hub on Apr 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill facilitates access to the Seoul Open Data API through a proxy architecture, which prevents the exposure of sensitive API keys within the agent's execution environment.
  • [COMMAND_EXECUTION]: The skill utilizes the curl command to fetch data from the station arrival endpoint. This execution is scoped to a specific task and uses safe parameters like --data-urlencode for station name inputs.
  • [PROMPT_INJECTION]: The skill ingests untrusted data from an external proxy. Ingestion point: API response from the proxy URL defined in SKILL.md. Boundary markers: Absent. Capability inventory: Includes curl for network requests. Sanitization: Absent. This represents a surface for indirect prompt injection, which is assessed as a low-severity risk factor.
  • [SAFE]: Proper guidance is provided regarding environment variable management (KSKILL_PROXY_BASE_URL), ensuring that the tool remains flexible and doesn't rely on hardcoded or sensitive endpoints.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 13, 2026, 01:00 AM
Security Audit — agent-trust-hub — seoul-subway-arrival