scrivener-compile

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local Python CLI script (cli.py) located in the plugin's tool directory. This script is responsible for reading the Scrivener project's binder and assembling the documents into the final output format.
  • [EXTERNAL_DOWNLOADS]: The documentation references well-known external software like Pandoc and LaTeX for future feature support (e.g., exporting to DOCX, EPUB, and PDF). These are recognized as trusted tools for document conversion.
  • [PROMPT_INJECTION]: The skill processes content from user-provided files within a .scriv project, which constitutes an indirect prompt injection surface.
  • Ingestion points: Project binder items, document titles, and body text from the .scriv package.
  • Boundary markers: The skill does not currently define specific delimiters or instructions to ignore embedded instructions in the processed manuscript data.
  • Capability inventory: Use of a local Python CLI tool for file system reading and output generation.
  • Sanitization: No explicit sanitization or filtering of the file content is described before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 12:26 PM
Security Audit — agent-trust-hub — scrivener-compile