writing-assistant

Pass

Audited by Gen Agent Trust Hub on Mar 30, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or security vulnerabilities were detected. The skill operates entirely through natural language instructions and local workspace file management.
  • [PROMPT_INJECTION]: Instructions include stylistic constraints (e.g., 'Never use filler phrases') which are benign and intended for quality control. No attempts to bypass safety filters or override system instructions were found.
  • [DATA_EXFILTRATION]: There are no network operations or external data transmissions. The documentation explicitly warns the user to keep sensitive information local and to review all outputs before sending or publishing.
  • [COMMAND_EXECUTION]: The skill does not utilize shell commands, subprocesses, or dynamic context injection patterns.
  • [EXTERNAL_DOWNLOADS]: No third-party packages, scripts, or remote assets are downloaded or executed by the skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 30, 2026, 12:22 AM