running-design-reviews
Pass
Audited by Gen Agent Trust Hub on Feb 19, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE] (SAFE): No malicious code, obfuscation, or persistence mechanisms detected across the 10 files. The content is purely informational and template-driven.
- [NO_CODE] (SAFE): The skill does not package any executable code (Python, Node.js, or Shell scripts) and has no external package dependencies.
- [CREDENTIALS_UNSAFE] (SAFE): The skill demonstrates best practices by explicitly instructing the agent in
SKILL.mdandreferences/CHECKLISTS.mdnot to request or record secrets or credentials. - [DATA_EXFILTRATION] (SAFE): There are no commands or instructions that attempt to access sensitive system files (e.g., SSH keys, env files) or exfiltrate data to external domains.
- [PROMPT_INJECTION] (SAFE): No malicious prompt injection patterns, role-play attacks (DAN), or instructions to bypass safety filters were found. The instructional language used is standard for task-specific guidance.
Audit Metadata