writing-fragments

Pass

Audited by Gen Agent Trust Hub on Aug 12, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill manages a local markdown file by reading, appending, and editing text fragments. These operations are performed on a file path provided by the user and represent the primary functional scope of the skill.
  • [PROMPT_INJECTION]: There is a potential surface for indirect prompt injection because the skill is instructed to re-read the target markdown file from disk to incorporate external changes. This allows content within the file to enter the agent's context.
  • Ingestion points: Markdown file at a user-defined path (SKILL.md).
  • Boundary markers: None are specified; the skill processes the file as a collection of raw fragments.
  • Capability inventory: Local file system read and write/append operations (SKILL.md).
  • Sanitization: No sanitization or filtering of the file content is performed, as the skill is intended to preserve raw user writing.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 12, 2026, 11:11 AM
Security Audit — agent-trust-hub — writing-fragments