wait-what
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides purely instructional content to modify the agent's output format and tone. No malicious patterns such as command execution, credential access, or data exfiltration were identified.
- [SAFE]: The skill configuration explicitly disables model tool invocation, which significantly reduces the potential attack surface by preventing the agent from calling external tools during execution.
Audit Metadata