scrivener-import

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses a local Python CLI (cli.py) to manage Scrivener projects. It executes subcommands like outline, find, and add to query and modify project files.
  • [EXTERNAL_DOWNLOADS]: The documentation references planned support for external tools like Pandoc and Textutil for document conversion. These are currently described as optional, engine-gated features and are not being downloaded or installed by the skill.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface due to its document import functionality.
  • Ingestion points: File content is read through the --text-file parameter in the add command.
  • Boundary markers: No markers are used to delimit the imported text or instruct the agent to ignore instructions within the data.
  • Capability inventory: The CLI tool supports writing documents and folders to the local filesystem within the Scrivener project.
  • Sanitization: There is no mention of sanitization or validation of the ingested file content before the import.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 12:26 PM
Security Audit — agent-trust-hub — scrivener-import