chapter-drafter
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill includes a Deno script (
scripts/score-scene.ts) used for calculating editorial scores based on pass/fail criteria. Analysis of the script shows it performs local mathematical calculations on provided JSON data and does not engage in risky behaviors such as network requests, file system modifications (beyond the requested--allow-read), or dynamic code evaluation. - [REMOTE_CODE_EXECUTION]: No remote code execution patterns or downloads from untrusted sources were detected. The skill relies on internal templates and a local script.
- [DATA_EXFILTRATION]: No data exfiltration patterns were detected. The skill processes fiction outlines and drafts locally within the agent's provided environment.
- [PROMPT_INJECTION]: The instructions are focused on structured editorial workflows. There are no attempts to bypass safety filters or override the agent's core instructions for malicious purposes.
Audit Metadata