oracle-consult
Pass
Audited by Gen Agent Trust Hub on Jul 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to utilize a CLI tool named
oracleand a PowerShell wrapper script (scripts/oracle-gate.ps1) to facilitate communication with an external expert model. These commands are configured with parameters for dry-runs and manual logins to maintain oversight. - [DATA_EXFILTRATION]: The workflow describes the process of sending selected files to an external service. To mitigate risk, the skill includes strict policy instructions to refuse context containing secrets, credentials, cookies, tokens, or unredacted private data, supported by a dry-run requirement.
Audit Metadata