writing-shape
Pass
Audited by Gen Agent Trust Hub on May 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's functionality is restricted to markdown processing and file management within the local user workspace. No access to sensitive system directories, credentials, or network resources is requested.
- [PROMPT_INJECTION]: Indirect prompt injection analysis: 1. Ingestion points: The skill reads a user-provided markdown file ('the pile') as its primary input. 2. Boundary markers: Absent in the instructions. 3. Capability inventory: Local file read and write operations via standard agent tools. 4. Sanitization: No explicit filtering of the input material. The risk associated with this ingestion surface is minimal because the instructions frame the content strictly as raw data to be 'mined' and 'reworked' for an article, which aligns with the skill's primary purpose.
Audit Metadata