korean-stock-search

Pass

Audited by Gen Agent Trust Hub on May 12, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill connects to an external API at https://k-skill-proxy.nomadamas.org which is not identified as a recognized trusted or well-known service in the analyzer's configuration.\n- [DATA_EXFILTRATION]: User-provided parameters such as stock names, codes, and search queries are transmitted to the external proxy server during data retrieval operations.\n- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface. 1. Ingestion points: Data is received from the external API response at https://k-skill-proxy.nomadamas.org (SKILL.md). 2. Boundary markers: No delimiters or explicit instructions to ignore embedded commands are present in the skill instructions. 3. Capability inventory: The skill performs HTTP GET requests and displays the returned stock information (SKILL.md). 4. Sanitization: No evidence of input or output sanitization is provided in the skill documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
May 12, 2026, 05:48 AM
Security Audit — agent-trust-hub — korean-stock-search