using-cloud-cli

Pass

Audited by Gen Agent Trust Hub on May 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill contains patterns for managing cloud resources via standard CLI tools including aws, gcloud, and bq. These operations are intended for administrative use.
  • [PROMPT_INJECTION]: The helper script scripts/bq-cost-check.sh presents a surface for indirect prompt injection as it accepts SQL queries for cost estimation. 1. Ingestion points: Command-line argument in scripts/bq-cost-check.sh. 2. Boundary markers: Input is handled with shell quoting. 3. Capability inventory: Executes BigQuery dry-run commands. 4. Sanitization: No independent validation of the query string is performed. This surface is inherent to the script's primary utility and is considered safe in the context of cloud administration tools.
Audit Metadata
Risk Level
SAFE
Analyzed
May 27, 2026, 09:30 AM
Security Audit — agent-trust-hub — using-cloud-cli