blind-johari-window
Pass
Audited by Gen Agent Trust Hub on Aug 7, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of descriptive text providing a mental model for evaluating self-knowledge and team dynamics. It does not perform any functional actions.
- [NO_CODE]: There are no scripts, binaries, or configuration files included that would execute code or invoke tools.
- [PROMPT_INJECTION]: The instructions do not contain any patterns intended to bypass AI safety guidelines, jailbreak the agent, or override system prompts.
- [DATA_EXFILTRATION]: No mechanisms for accessing sensitive local data, environment variables, or transmitting data to external servers were identified.
- [REMOTE_CODE_EXECUTION]: The skill does not download external resources or execute remote scripts.
Audit Metadata