writing

Pass

Audited by Gen Agent Trust Hub on Aug 3, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill instructions (SKILL.md) and reference files (references/) contain legitimate heuristics for writing and editing, such as the Minto Pyramid and ABT spine. No prompt injection or bypass attempts were detected.
  • [COMMAND_EXECUTION]: The shell script evals/run-static-checks.sh is a development utility for validating skill integrity. It executes a local Python script for static analysis and does not perform any dangerous operations.
  • [EXTERNAL_DOWNLOADS]: The README.md file contains installation instructions using npx to fetch the author's skill kit. This is a documented distribution method and no unauthorized or suspicious external downloads were identified.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 3, 2026, 05:28 PM
Security Audit — agent-trust-hub — writing