ns-rewrite-light

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local Python utility script at 'skills/ns-draft/scripts/chapter_audit.py' to perform word count audits on novel chapters.- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it processes untrusted novel text for rewriting.
  • Ingestion points: User-supplied novel segments for light editing (SKILL.md).
  • Boundary markers: Not present.
  • Capability inventory: Execution of a local word-counting script (SKILL.md).
  • Sanitization: None specified for the input segments.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 06:47 AM