draft-and-revise

Pass

Audited by Gen Agent Trust Hub on Jun 23, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists entirely of markdown instructions and metadata designed to improve the agent's writing output through a self-critique loop.
  • [SAFE]: No external network operations, remote script downloads, or sensitive file system accesses are present. The skill relies entirely on the agent's internal reasoning capabilities.
  • [SAFE]: Metadata fields, including the source repository 'github.com/synthesisengineering/ragbot', are consistent with the identified author 'Synthesis Engineering' and represent standard vendor documentation.
  • [SAFE]: No obfuscation, prompt injection attempts, or persistence mechanisms were detected in the instructions or the rubric configuration.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 23, 2026, 12:55 AM
Security Audit — agent-trust-hub — draft-and-revise