scrivener-edit

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes a local Python script located at ${CLAUDE_PLUGIN_ROOT}/tools/scrivener/cli.py to perform operations on Scrivener project files. This is the primary mechanism for reading binder structures and modifying RTF content.
  • [SAFE]: The skill implements extensive safety guidelines, including explicit instructions to close the target application to prevent file corruption and automated timestamped backups (zip archives) before any destructive operations.
  • [SAFE]: No patterns of remote code execution, unauthorized network access, or data exfiltration were detected in the analyzed files.
  • [SAFE]: The skill handles rich text content (RTF) using a 'token-preserving' model to prevent loss of metadata like comments and footnotes, and it includes a safeguard ('rich-doc guard') that prevents accidental overwriting of complex documents without an explicit override.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 12:26 PM
Security Audit — agent-trust-hub — scrivener-edit