write-technical-docs
Pass
Audited by Gen Agent Trust Hub on Aug 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill contains only Markdown instructions and reference files. It does not include any scripts, binaries, or automation that would execute code or interact with the operating system.
- [EXTERNAL_DOWNLOADS]: The reference files contain links to the official Google Developer Documentation Style Guide (developers.google.com). These links are for reference purposes and do not trigger any automated downloads or script executions.
- [CREDENTIALS_UNSAFE]: The guidelines include proactive security instructions, explicitly stating: 'Never place secrets, live credentials, real personal data, or production endpoints in examples.' This ensures that the agent helps users maintain credential security.
- [PROMPT_INJECTION]: The instructions are designed to guide documentation tasks and do not contain any patterns intended to bypass AI safety guards, extract system prompts, or override agent behavior maliciously.
- [DATA_EXFILTRATION]: There are no commands or instructions that could result in the exfiltration of user data. The skill focuses solely on the editorial quality and technical accuracy of provided documentation within the session context.
Audit Metadata