technical-writing

Pass

Audited by Gen Agent Trust Hub on Aug 2, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a reference for high-quality technical writing. It provides rules for sentence structure, terminology, and document modes without introducing any executable scripts or high-risk instructions.- [EXTERNAL_DOWNLOADS]: The skill references several external sources for its documentation standards, including diataxis.fr, developers.google.com/style, asd-ste100.org, and Internet Archive links for style guides. These are reputable and well-known industry resources for technical writers and do not represent a security risk.- [PROMPT_INJECTION]: The skill contains instructional language for the AI agent (e.g., "Apply all four [layers]", "Cut every word that does no work"), but these are stylistic constraints for content generation and do not attempt to bypass safety filters, extract system prompts, or override agent identity.- [COMMAND_EXECUTION]: The text includes an example of a shell command (budget.mjs --write) within a "Worked example" section. This is used strictly for illustrative purposes to demonstrate how to write documentation for scripts and does not instruct the agent to execute any local commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 2, 2026, 01:29 PM
Security Audit — agent-trust-hub — technical-writing