novel-script
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
Bashtool to run its internal Node.js utility (scripts/novel-script.mjs) for screenplay seeding, validation, and rendering. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted JSON data from various external files which could contain malicious instructions.
- Ingestion points: Reads
outline.json,script.json,art.json, andcast.jsonvia command-line arguments. - Boundary markers: Relies on strict JSON structure and programmatic validation rather than natural language delimiters.
- Capability inventory: Significant capabilities including
Bash(for tool execution),Read(for data ingestion), andWrite(for saving scripts). - Sanitization: The rendering engine in
scripts/novel-script.mjsimplements robust sanitization using theesc()function to encode HTML entities and JSON escaping to prevent XSS in generated HTML reports.
Audit Metadata