sdd-riper-one-light
Pass
Audited by Gen Agent Trust Hub on May 8, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill implements 'Restate First' and 'Checkpoint' mechanisms as operational controls to prevent mission drift and ensure the agent stays aligned with the user's original intent.
- [DATA_EXFILTRATION]: The instructions explicitly prohibit the exfiltration of sensitive data, specifically naming API keys, trace logs, and machine-private paths as items to be protected.
- [COMMAND_EXECUTION]: The skill includes a local Python script (
scripts/default_prompt_check.py) used to scan and update AI configuration files (e.g., .cursorrules, CLAUDE.md). The script uses only the Python standard library and its execution is gated by mandatory user approval instructions. - [SAFE]: No malicious patterns, obfuscation, or unauthorized network activity were detected. The skill is designed as a safety harness to increase transparency and control over AI agent behavior.
Audit Metadata