skills/kucherenko/gangsta/omerta/Gen Agent Trust Hub

omerta

Pass

Audited by Gen Agent Trust Hub on Apr 26, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements governance guardrails and state management protocols.
  • [COMMAND_EXECUTION]: No shell commands or dangerous process executions were detected. The file-writing instructions for checkpoints are scoped to project-specific paths (docs/gangsta/).
  • [DATA_EXFILTRATION]: No network operations or access to sensitive system files (e.g., SSH keys, AWS credentials) were found.
  • [PROMPT_INJECTION]: The skill uses thematic role-play ('Gangsta Borgata') to define operational constraints, but does not contain instructions to bypass AI safety filters or ignore system prompts.
  • [EXTERNAL_DOWNLOADS]: No external packages, remote scripts, or third-party dependencies are referenced.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 26, 2026, 06:23 AM