writing
Pass
Audited by Gen Agent Trust Hub on May 20, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues were detected during the analysis of the skill files. All analyzed content consists of stylistic guidelines and internal development specifications.
- [PROMPT_INJECTION]: The skill uses instructional language to guide the AI's writing style but does not contain commands to override system prompts or bypass safety filters.
- [DATA_EXFILTRATION]: There are no network operations or instructions to access sensitive local files. The specification file explicitly prohibits the storage of secrets and credentials in the skill or its references.
- [COMMAND_EXECUTION]: While the specification mentions local validation scripts used for testing and evaluation (e.g., distiller.py), these are part of the development environment and do not pose a risk of arbitrary command execution via user input.
- [CREDENTIALS_UNSAFE]: No hardcoded API keys, tokens, or other credentials were found. The skill includes a clear policy against leaking machine paths or secrets.
Audit Metadata