seoul-density
Pass
Audited by Gen Agent Trust Hub on May 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches real-time data from the vendor's proxy endpoint at
https://k-skill-proxy.nomadamas.org. This is used to provide the skill's primary functionality by accessing the Seoul Open Data API.\n- [COMMAND_EXECUTION]: Implements a single-entrypoint CLI script. Analysis ofscripts/seoul_density.pyshows it uses safe practices for input handling and does not invoke external shell commands or arbitrary code.\n- [PROMPT_INJECTION]: As the skill ingests data from an external API, it possesses an indirect prompt injection surface. Malicious content within the API response could potentially attempt to influence the agent.\n - Ingestion points: API response data processed in
scripts/seoul_density.pyviafetch_density_via_proxy.\n - Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the output.\n
- Capability inventory: The skill is limited to performing network GET requests to the specified proxy URL.\n
- Sanitization: The script parses structured JSON data but does not perform sanitization on string fields displayed to the user.
Audit Metadata