genkit-infra-expert

Pass

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill performs standard infrastructure-as-code operations using Terraform and gcloud. No malicious intent or security vulnerabilities were identified.
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute terraform and gcloud commands. These actions are restricted to the intended scope of provisioning and managing Google Cloud infrastructure for Genkit applications.
  • [DATA_EXFILTRATION]: Analysis of the shell script and skill instructions shows no attempts to access sensitive local files or exfiltrate data to external domains.
  • [SAFE]: An indirect prompt injection surface exists in the project configuration script where user-provided identifiers are used to generate Terraform files. 1. Ingestion points: PROJECT_ID and REGION arguments in scripts/init-terraform.sh. 2. Boundary markers: None; variables are used in a heredoc template. 3. Capability inventory: Bash execution of terraform and gcloud binaries. 4. Sanitization: No explicit sanitization of input variables, relying on the caller for valid project identifiers.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 13, 2026, 12:14 PM