vertex-engine-inspector
Pass
Audited by Gen Agent Trust Hub on Mar 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's functionality is strictly limited to inspecting and validating cloud deployment configurations as described in its metadata. No malicious patterns, obfuscation, or persistence mechanisms were detected.\n- [COMMAND_EXECUTION]: The skill performs shell commands via
gcloudandcurl. Analysis of the implementation shows that commands are constructed safely using list-based arguments in Python and properly quoted variables in Bash, preventing shell injection.\n- [DATA_EXFILTRATION]: Although the skill accesses sensitive IAM policies and deployment metadata, this information remains within the agent's context for report generation. No network requests to external, non-whitelisted domains were identified for data transfer.\n- [EXTERNAL_DOWNLOADS]: Connectivity checks performed usingcurltarget specified agent endpoints for protocol validation. These operations do not involve downloading or executing remote code or scripts.
Audit Metadata