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