korean-stock-search

Pass

Audited by Gen Agent Trust Hub on Apr 18, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill makes HTTPS GET requests to k-skill-proxy.nomadamas.org to retrieve stock listings and trade snapshots. This is a vendor-managed resource provided for the skill's functionality.\n- [DATA_EXFILTRATION]: User-provided search terms (stock names and codes) are sent to the proxy endpoint. No unauthorized access to local files or exfiltration of sensitive information was detected.\n- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it processes external API data.\n
  • Ingestion points: API responses from k-skill-proxy.nomadamas.org are presented to the agent context.\n
  • Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the skill definition.\n
  • Capability inventory: The skill performs network GET requests but does not possess capabilities for file writing, subprocess execution, or accessing system credentials.\n
  • Sanitization: No explicit response validation or sanitization is mentioned in the SKILL.md.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 18, 2026, 05:05 PM