tighten-prose
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No security threats or malicious patterns were detected in the instructions or metadata. The skill follows its stated purpose of prose editing.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied drafts, which constitutes a vulnerability surface for indirect prompt injection. 1. Ingestion points: User-provided draft text in the prompt or from existing notes. 2. Boundary markers: None explicitly defined to distinguish instructions from content. 3. Capability inventory: Integration with Scratchpad and other notes tools for file creation and modification. 4. Sanitization: No automated sanitization is specified, but the skill mandates a human-in-the-loop checkpoint by requiring user approval before any text is replaced.
Audit Metadata