craft-author-voice
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's primary functions are reading and writing a local style guide (
AUTHOR_VOICE.md) based on user interaction. It does not perform unauthorized network operations, execute remote code, or exhibit signs of obfuscation. - [DATA_EXPOSURE]: The skill reads existing
AUTHOR_VOICE.mdfiles to allow refinement. This is limited to the local environment and the intended scope of the writing assistant. - [INDIRECT_PROMPT_INJECTION]: The skill ingests content from an existing
AUTHOR_VOICE.mdfile if found. While this is an external data source, it is processed as text to be displayed or refined by the user, and no sensitive capabilities (like code execution or network exfiltration) are triggered by this data.
Audit Metadata