terraform-drift-detection

Warn

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection (MEDIUM): The skill is vulnerable to indirect injection because it ingests data from external AWS resources into the agent's decision-making loop.
  • Ingestion points: drift.json (generated from terraform show -json).
  • Boundary markers: Absent. The agent processes the raw JSON output to categorize drift and recommend actions.
  • Capability inventory: Execution of terraform apply and terraform apply -refresh-only based on agent recommendations.
  • Sanitization: Absent. Maliciously crafted AWS resource tags or names could influence the agent's categorization or impact assessment.
  • Command Execution (MEDIUM): The skill explicitly executes system commands including aws sts get-caller-identity, terraform init, and terraform plan. While essential for the skill's purpose, this grants the agent control over the cloud environment's state and configuration.
  • Data Exposure (MEDIUM): Terraform state and plan files (drift.json) often contain sensitive plain-text information such as database passwords, API keys, or private environment variables. Reading this data into the LLM context constitutes a risk of sensitive data exposure to the model provider.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 01:17 PM