agent-writing

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFE
Full Analysis
  • [DYNAMIC_EXECUTION]: The file tests/test_check_prose.py utilizes importlib.util to dynamically load and execute the scripts/check_prose.py script during unit testing. This is a standard development practice for testing local scripts that are not installed as packages.
  • [COMMAND_EXECUTION]: The main instructions in SKILL.md direct the agent to execute a local Python script (scripts/check_prose.py) to validate documentation style. The script is part of the skill's own source code and performs read-only analysis of local Markdown files.
  • [EXTERNAL_DOWNLOADS]: The skill references the official Google developer documentation style guide and a public GitHub repository from Cursor. These are well-known, trusted sources used for stylistic reference and do not involve the automated fetching of executable payloads.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 12:20 AM
Security Audit — agent-trust-hub — agent-writing