setup-cann-wiki

Pass

Audited by Gen Agent Trust Hub on May 18, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses shell commands to check the status of a local server (curl), detect installed tools (command -v), and configure the agent (claude mcp add). It also provides instructions to start a local Python server.
  • [EXTERNAL_DOWNLOADS]: The skill references an external repository (AscendC-Kernel-Wiki) and assumes the user has access to it. It does not perform any automated downloads from remote sources.
  • [DATA_EXFILTRATION]: No data exfiltration patterns were detected. Network activity is limited to checking a local port (localhost:3000).
Audit Metadata
Risk Level
SAFE
Analyzed
May 18, 2026, 09:28 AM
Security Audit — agent-trust-hub — setup-cann-wiki