dsh-prose-standard

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is a pure instructional set for prose quality and documentation standards. It does not include executable code, external dependencies, or network-enabled operations.
  • [SAFE]: It implements explicit path exclusions for vendor/ directories and archived agent notes, which is a defensive best practice to prevent the agent from modifying sensitive or third-party codebases.
  • [SAFE]: The guidance focuses on preserving 'contracts' (preconditions, postconditions, and security boundaries) within documentation, ensuring that security-relevant information in comments is not removed during trimming processes.
  • [SAFE]: No obfuscation, prompt injection, or data exfiltration vectors were identified. The workflow requires explicit user-defined scopes and defaults to an 'automatic' mode that reports findings without making unauthorized changes unless specifically requested.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 09:44 AM
Security Audit — agent-trust-hub — dsh-prose-standard