qodo-setup
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements defensive instructions that explicitly prevent common attack vectors, such as piping remote scripts into a shell or asking users to paste credentials directly into the conversation.
- [COMMAND_EXECUTION]: The skill uses local shell and PowerShell commands to interact with the Qodo CLI. These operations are limited to version checking, identity verification, and tool catalog refreshing, with specific gates for version compatibility (0.1.0-next.37 or newer).
- [INDIRECT_PROMPT_INJECTION]: The skill monitors tool output for structured notices (
QODO_NOTICE). While this is a data ingestion point, the skill mitigates risk by requiring the agent to perform a read-only inventory and obtain explicit user approval before executing any update commands. - [EXTERNAL_DOWNLOADS]: The skill directs users to the vendor's official site (
get.qodo.ai) for CLI installation rather than attempting to download or execute code automatically.
Audit Metadata