ns-write

Pass

Audited by Gen Agent Trust Hub on Apr 30, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute local Python scripts included in the skill package (chapter_audit.py, export_text.py) and a referenced tool (word_count.py) for word count auditing and text export operations within the novel project structure.
  • [DATA_EXFILTRATION]: No network operations or access to sensitive system files (e.g., credentials, SSH keys, environment variables) were detected. The skill operates strictly on project-specific configuration files (e.g., memory.yaml, continuity.yaml) and story content.
  • [PROMPT_INJECTION]: The instructions do not contain attempts to bypass safety filters, extract system prompts, or override agent constraints.
  • [SAFE]: No obfuscation (Base64, zero-width characters), persistence mechanisms, or privilege escalation patterns were identified. The skill's behavior is consistent with its stated purpose of managing novel writing projects.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 30, 2026, 05:56 PM