scrivener-extract
Pass
Audited by Gen Agent Trust Hub on Jun 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security vulnerabilities were identified in the skill. The operations are entirely local and focus on data conversion from internal Scrivener file formats to standard text formats.
- [COMMAND_EXECUTION]: The skill uses a local CLI tool (
cli.py) for extraction tasks. The usage patterns are well-defined and rely on internal environment paths (CLAUDE_PLUGIN_ROOT), maintaining a restricted execution context. - [DATA_EXPOSURE]: The skill accesses project files on disk as intended for its core functionality. It is explicitly described as read-only and does not perform any network calls or access sensitive user credentials or system configurations.
- [PROMPT_INJECTION]: The instructions do not contain any commands that attempt to bypass safety guidelines or override agent behavior. While it processes external RTF data, the technical implementation described (a conservative parser that strips placeholders) mitigates risks associated with indirect prompt injection.
Audit Metadata