ghostwriter-pro

Pass

Audited by Gen Agent Trust Hub on Apr 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes external manuscript data, creating a potential surface for indirect prompt injection where instructions in a text file could attempt to influence agent behavior. This is an inherent risk of tools that process natural language text.
  • Ingestion points: Chapter and scene text ingested during pacing analysis and dialogue polishing.
  • Boundary markers: None identified.
  • Capability inventory: File read and write permissions are used to manage project content.
  • Sanitization: No explicit sanitization or filtering of input text is defined.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 18, 2026, 12:42 AM
Security Audit — agent-trust-hub — ghostwriter-pro