fiction-layout-exporter

Pass

Audited by Gen Agent Trust Hub on Aug 9, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues detected. The skill's functionality is consistent with its stated purpose of formatting text files into document layouts.
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute a local Python script helpers/python/generate_fiction_docx.py. This is a routine operation for a layout generation tool and operates on local paths within the skill's environment.
  • [INDIRECT_PROMPT_INJECTION]: The skill identifies an attack surface for indirect prompt injection through manuscript files.
  • Ingestion points: Data is ingested from chapters/full_manuscript.md via the --input flag in the command execution.
  • Boundary markers: None explicitly defined in the prompt instructions.
  • Capability inventory: The skill has the capability to execute shell commands (python ...).
  • Sanitization: No specific sanitization or validation steps for the manuscript content are mentioned in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 9, 2026, 11:35 AM
Security Audit — agent-trust-hub — fiction-layout-exporter