writing-fragments

Pass

Audited by Gen Agent Trust Hub on Jul 8, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill performs file system operations, specifically reading from and appending to a local markdown file. These actions are triggered by user interaction and are necessary for the skill's stated purpose of managing a writing document.
  • [PROMPT_INJECTION]: The skill involves reading a local file that might be edited externally, creating a potential surface for indirect prompt injection. However, the instructions guide the agent to treat the file content as raw writing material rather than instructions, and the capabilities are limited to basic file management, making the risk negligible.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 8, 2026, 01:56 AM
Security Audit — agent-trust-hub — writing-fragments