jww-writing-style
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions for drafting and revising prose in a specific style. No executable code, scripts, or automation logic are present.
- [PROMPT_INJECTION]: No attempts to override safety filters, bypass instructions, or escalate privileges were detected. The instructions include explicit guardrails, such as stating that drafting does not authorize sending or accessing message history.
- [DATA_EXPOSURE]: There are no commands that access sensitive files, environment variables, or hardcoded credentials.
- [REMOTE_CODE_EXECUTION]: No external dependencies, package installations, or remote script downloads are requested.
- [OBFUSCATION]: The text is clear and contains no encoded strings, hidden characters, or homoglyphs. The UUID referenced in the 'Basis and limits' section appears to be a standard reference to a chat session history for provenance.
- [INDIRECT_PROMPT_INJECTION]: While the skill is designed to process user-provided text for revision (representing an ingestion point), it lacks any tools or capabilities (such as network access or file writing) that could be exploited through malicious data. The risk is negligible.
Audit Metadata