using-cloud-cli
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- Indirect Prompt Injection (LOW): The skill is susceptible to indirect prompt injection through its cloud query execution surface.
- Ingestion points: The script
scripts/bq-cost-check.shaccepts a SQL query as a command-line argument ($1). - Boundary markers: There are no delimiters or specific instructions to the agent to treat the input query as untrusted data.
- Capability inventory: The skill allows execution of
bq(BigQuery),gcloud, andawsCLI commands via theBashtool. - Sanitization: No input validation or sanitization is performed on the query string before it is passed to the
bqcommand. - Command Execution (SAFE): The documented commands and the cost-checking script are standard administrative utilities. The inclusion of
--dry-runand cost estimation logic follows operational best practices. - Data Exposure & Exfiltration (SAFE): No hardcoded credentials or sensitive file access patterns were identified. Network operations are restricted to official cloud service endpoints (GCP/AWS).
Audit Metadata