faf-go

Pass

Audited by Gen Agent Trust Hub on Aug 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
  • [SAFE]: The skill utilizes standard tools like AskUserQuestion and TodoWrite for its primary interview workflow. These are native tools designed for safe user-agent interaction and state management.
  • [COMMAND_EXECUTION]: The instructions involve running local commands such as faf score, faf go, and faf sync, as well as reading the project.faf file. These actions are consistent with the skill's stated purpose of managing .faf configuration and do not involve unauthorized privilege escalation or suspicious shell operations.
  • [DATA_EXFILTRATION]: No network requests or data transmission patterns to external domains were identified. The skill's operations are confined to the local project environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 11, 2026, 08:49 PM
Security Audit — agent-trust-hub — faf-go