korean-stock-search

Pass

Audited by Gen Agent Trust Hub on Apr 13, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill retrieves financial information from the external domain k-skill-proxy.nomadamas.org. This interaction is consistent with the skill's core purpose of providing access to Korean stock data without requiring local API keys.\n- [COMMAND_EXECUTION]: Utilizes curl to perform network requests to the proxy API for data retrieval. These commands are restricted to fetching JSON data and do not include administrative or privileged operations.\n- [DATA_EXFILTRATION]: Transmits user-provided stock names and codes to the external proxy server to retrieve matching results. No sensitive local files, environment variables, or credentials are accessed or transmitted.\n- [PROMPT_INJECTION]: The skill processes data from an external source, which presents an attack surface for indirect prompt injection.\n
  • Ingestion points: JSON responses from the k-skill-proxy.nomadamas.org endpoints (SKILL.md).\n
  • Boundary markers: Absent; external data is integrated into the agent context without specific isolation or ignore markers.\n
  • Capability inventory: Network operations via curl (SKILL.md).\n
  • Sanitization: No explicit validation or sanitization of the remote API response is specified before it is processed.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 13, 2026, 01:00 AM
Security Audit — agent-trust-hub — korean-stock-search