improve-writing
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill is composed entirely of natural language instructions for the AI agent. It does not include any scripts, executable commands, or configuration files that could perform actions on a host system.
- [SAFE]: No network activity, file system interactions, or credential management patterns were identified. The instructions are focused solely on linguistic and structural improvements to writing.
- [INDIRECT_PROMPT_INJECTION]: The skill is intended to process external data provided by the user, such as prose, slack messages, and emails.
- Ingestion points: User-supplied text inputs mentioned in the description and guidance sections of SKILL.md.
- Boundary markers: None present.
- Capability inventory: The skill has no defined functional capabilities or tool access, such as subprocess calls, file-write operations, or network access.
- Sanitization: None present.
- Assessment: Due to the complete absence of actionable tools or system access, the risk associated with this ingestion surface is negligible.
Audit Metadata