setup-icp-md
Pass
Audited by Gen Agent Trust Hub on Aug 6, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns detected. The skill's behavior is consistent with its stated purpose.
- [EXTERNAL_DOWNLOADS]: The skill uses web search tools to collect market signals from external websites.
- [DATA_EXFILTRATION]: The skill reads project documentation and code to inform its research; this local data is used as input for web searches.
- [PROMPT_INJECTION]: The skill ingests untrusted data from the web, which is an architectural surface for indirect prompt injection, though no exploitation instructions are present in the skill itself.
Audit Metadata