technical-writing
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a pure documentation guideline. It consists entirely of natural language instructions for the AI agent to follow when writing or reviewing technical documentation.
- [NO_CODE]: There are no scripts, binaries, or configuration files that execute code. The frontmatter includes
disable-model-invocation: true, which is a security-enhancing configuration that prevents the skill from triggering external model calls. - [PROMPT_INJECTION]: The instructions provide guidance on writing style (active voice, short words, Diátaxis modes) and do not attempt to bypass safety filters or override system instructions.
- [DATA_EXFILTRATION]: No patterns for accessing sensitive files (like credentials or SSH keys) or sending data to external servers were identified.
- [EXTERNAL_DOWNLOADS]: The skill references legitimate external documentation sources (diataxis.fr, developers.google.com, asd-ste100.org) for attribution purposes, but it does not attempt to download or execute content from them.
Audit Metadata