writing-skills

Pass

Audited by Gen Agent Trust Hub on Mar 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The utility script render-graphs.js utilizes child_process.execSync to execute the Graphviz dot command-line tool. It pipes markdown-extracted content into the process via standard input and performs filesystem operations to read and write diagram files.
  • [PROMPT_INJECTION]: The skill teaches 'Persuasion Principles' designed to override an agent's tendency to rationalize or bypass constraints. This includes the use of 'Authority' language such as 'YOU MUST' and 'No exceptions' to establish non-negotiable behavioral boundaries and binding meta-instructions like 'Violating the letter of the rules is violating the spirit.'
  • [SAFE]: The skill incorporates official authoring best practices and recommends standard, well-known libraries for file processing, such as pdfplumber and pypdf.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 22, 2026, 01:08 PM