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
Risk Level
SAFE
Analyzed
Aug 6, 2026, 01:40 PM
Security Audit — agent-trust-hub — setup-icp-md