linkedin-ghostwriting

Pass

Audited by Gen Agent Trust Hub on Mar 24, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's primary purpose is text generation for LinkedIn content. It does not perform any network operations, file system modifications (beyond those permitted for a coding agent to read its own files), or command execution.
  • [SAFE]: No prompt injection attempts or instructions to bypass safety guidelines were found. The workflow explicitly requires user interaction and validation before proceeding between phases.
  • [SAFE]: The evaluation cases in evals/evals.json are standard functional tests ensuring the agent adheres to the defined persona and logic.
  • [SAFE]: No obfuscated content, hardcoded credentials, or remote code execution patterns were identified.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 24, 2026, 01:35 PM