refactor-ruthless-editor
Pass
Audited by Gen Agent Trust Hub on Jul 6, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes a local Node.js script (
scripts/checklist.mjs) to calculate word counts and reduction percentages between document drafts. This script is self-contained, has zero external dependencies, and performs no network operations. - [DATA_EXFILTRATION]: No network access or data exfiltration patterns were identified. The skill only processes text provided within the agent's context and logs changes locally to provided templates.
- [PROMPT_INJECTION]: The instructions are strictly focused on text editing and summarization. There are no attempts to bypass safety filters, override system instructions, or extract sensitive model information.
- [REMOTE_CODE_EXECUTION]: The skill does not download or execute code from external or untrusted sources. All logic is contained within the provided markdown and JavaScript files.
- [SAFE]: The skill follows secure practices by explicitly excluding code blocks, identifiers, and configuration files from its editing process, preventing accidental corruption of technical assets.
Audit Metadata