ghostwriter-pro

Pass

Audited by Gen Agent Trust Hub on Aug 10, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's instructions are focused entirely on creative writing tasks. No malicious patterns such as obfuscation, hardcoded credentials, or suspicious remote code execution were found.
  • [PROMPT_INJECTION]: The skill processes user-provided content (chapters and scenes) and possesses file-writing capabilities, creating an inherent attack surface for indirect prompt injection. However, the instructions include a safety best practice by requiring explicit author approval before saving drafts generated in 'Deep Write Mode', which mitigates the risk of automated malicious file modifications.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 10, 2026, 07:41 PM
Security Audit — agent-trust-hub — ghostwriter-pro