cognitive-bias-design
Pass
Audited by Gen Agent Trust Hub on Jul 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No executable code or scripts were found in the skill, which minimizes the risk of arbitrary command execution or system compromise.\n- [SAFE]: The skill does not contain any network-related commands (such as curl or wget) or hardcoded credentials, ensuring no risk of data exfiltration or unauthorized access.\n- [SAFE]: Analysis of the skill instructions and the bias catalog revealed no signs of obfuscation, prompt injection, or hidden malicious commands.\n- [SAFE]: The skill includes explicit ethical guidelines that instruct the AI agent to redirect requests that attempt to exploit user vulnerabilities or use deceptive design patterns.
Audit Metadata