writing-fragments
Pass
Audited by Gen Agent Trust Hub on Aug 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill facilitates a creative writing process by capturing and saving text fragments to a local file. Its operations are transparent and scoped to a user-defined path.\n- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface due to its requirement to read from a local file to preserve user changes.\n
- Ingestion points: The agent reads the contents of the target markdown file provided by the user.\n
- Boundary markers: No delimiters are present to isolate file content from system instructions.\n
- Capability inventory: The skill uses file system read and write (append) capabilities.\n
- Sanitization: Content read from the file is not sanitized or filtered.
Audit Metadata