ask-mode
Pass
Audited by Gen Agent Trust Hub on Jul 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill configuration utilizes platform-level enforcement to minimize security risks. It explicitly disables automated execution (
autoExecute: false), the code bridge mechanism (codeBridge: false), and automatically strips code blocks from output (stripCodeBlocks: true). - [SAFE]: The instructions contain strict defensive rules prohibiting the generation of JavaScript or any other executable code blocks. This design prevents the agent from being used as a vector for script injection or accidental code execution.
- [SAFE]: No external dependencies, network operations, or sensitive file access patterns were identified in the configuration or instructions.
- [SAFE]: The skill restricts its tool access to a safe whitelist (
proofread-grammar,translate-text), adhering to the principle of least privilege.
Audit Metadata