writing-fragments
Pass
Audited by Gen Agent Trust Hub on Aug 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill functions as an interactive writing assistant that records user thoughts into a structured markdown document as intended.
- [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface because it re-reads user-controlled content from a markdown file to preserve manual edits. Ingestion points: The markdown file specified by the user or passed via path. Boundary markers: None present. Capability inventory: File read and write operations only. Sanitization: None explicitly defined. The risk is considered safe given the lack of sensitive data access or network capabilities.
- [SAFE]: No obfuscated URLs, remote code execution patterns, or unauthorized persistence mechanisms were identified in the instructions.
Audit Metadata