layers-observed-behaviour
Pass
Audited by Gen Agent Trust Hub on Aug 3, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions and organizational frameworks for conducting user research sessions. No malicious patterns were detected.
- [NO_CODE]: The skill does not include any executable scripts, shell commands, or configuration files that perform system operations.
- [DATA_EXFILTRATION]: No network operations or commands for sending data to external servers are present.
- [CREDENTIALS_UNSAFE]: No hardcoded secrets, API keys, or sensitive credentials were found in the skill content.
- [PROMPT_INJECTION]: The instructions do not attempt to override system safety guidelines or bypass AI behavioral constraints.
Audit Metadata