skills/gemini-cli-extensions/data-agent-kit-starter-pack/gcs-security-assessment/Gen Agent Trust Hub
gcs-security-assessment
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local Python scripts and system binaries like gcloud and curl to interact with Google Cloud APIs. These operations are essential for the skill's primary function of assessing cloud security posture and are performed using secure argument passing to avoid shell injection.
- [DYNAMIC_EXECUTION]: The cloud_rest_helpers_nodeps.py script uses subprocess.run to call curl for API communication. It protects sensitive data by storing OAuth2 tokens in temporary files rather than passing them as command-line arguments.
- [INDIRECT_PROMPT_INJECTION]: The skill processes telemetry data ingested from external BigQuery views. Ingestion point: BigQuery views (fetch_bucket_telemetry.py, fetch_object_telemetry.py). Boundary markers: Absent. Capability inventory: Subprocess calls to curl and gcloud (cloud_rest_helpers_nodeps.py). Sanitization: Input validation in validation.py and structured JSON parsing. This is assessed as safe due to robust data handling and the trusted source of the data.
Audit Metadata