constitutional-writer
Pass
Audited by Gen Agent Trust Hub on Mar 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security vulnerabilities were identified in the skill files. All operations are localized to document processing.
- [COMMAND_EXECUTION]: The skill utilizes a local Python script
scripts/extract_constitution.pyto process text documents. Analysis of the script confirms it uses safe regex-based extraction logic and does not execute arbitrary code or interact with external networks. - [DATA_EXFILTRATION]: No network operations, hardcoded secrets, or access to sensitive system files were detected in the instructions or scripts.
- [PROMPT_INJECTION]: The instructions are strictly focused on task performance and do not contain patterns typical of prompt injection, jailbreaking, or safety bypass attempts.
Audit Metadata