skills/edheltzel/do-skills/do-docs/Gen Agent Trust Hub

do-docs

Pass

Audited by Gen Agent Trust Hub on Oct 15, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill implements a structured workflow for documentation authorship and refinement based on the Diataxis framework. It includes rigorous 'gates' and interactive checkpoints to ensure documentation quality and maintain user control over all actions.
  • [INDIRECT_PROMPT_INJECTION]: The 'Improve' mode ingests content from local markdown files via a user-provided 'Path' argument as described in 'references/improve.md'. While this ingestion of external data creates a potential surface for indirect prompt injection, the skill mitigates this through strict structural classification rules, boundary markers (parsing by headings), and a mandatory interactive review process ('yes/skip/modify' loop) requiring explicit user approval before any file modification occurs. The capability inventory is limited to reading and writing documentation files.
  • [COMMAND_EXECUTION]: Documentation templates and examples within the skill include shell commands for software installation (e.g., 'npm install') and project setup. These are static, informational examples intended for the reader's documentation and do not involve autonomous command execution by the agent.
  • [NO_CODE]: The skill consists entirely of Markdown instructions and reference templates. It does not contain any executable scripts, binaries, or active code components.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 15, 2026, 12:46 AM