cloudcli
Pass
Audited by Gen Agent Trust Hub on Apr 8, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands (specifically
curl) to verify the status of a local service running onlocalhost:4681. This is a standard method for checking service health. - [COMMAND_EXECUTION]: The skill uses the
opencommand to launch a browser session to a specified URL. This is used for the intended purpose of accessing the web UI. - [DATA_EXPOSURE_AND_EXFILTRATION]: While the skill mentions token-based authentication, it does not attempt to read or exfiltrate credentials; it merely points the user to the configuration location.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from a local API (
/api/health). While this represents a theoretical attack surface if the local service were compromised, the risk is minimal given the specific context of a health check.
Audit Metadata