revise
Pass
Audited by Gen Agent Trust Hub on Apr 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: No security issues were detected in the skill's instructions or metadata. The skill focuses solely on providing editorial feedback and revision suggestions.
- [SAFE]: The requested permissions, file:read and file:write, are appropriate and necessary for the skill to perform its intended function of editing text files.
- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface (Category 8) because it processes untrusted text from files. 1. Ingestion points: Text provided for revision in files. 2. Boundary markers: Absent. 3. Capability inventory: file:read and file:write permissions. 4. Sanitization: No explicit sanitization of input text. This surface is evaluated as safe given the skill's limited scope as a writing assistant.
Audit Metadata