terraform-state-manager
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill identifies a vulnerability surface where the agent is instructed to build shell commands from user-provided data. 1. Ingestion points: User-provided parameters such as resource_address, cloud_id, and LOCK_ID. 2. Boundary markers: No delimiters or ignore instructions are used to separate untrusted input from the shell command. 3. Capability inventory: Use of the terraform CLI which executes local system operations. 4. Sanitization: The skill does not provide any validation or escaping instructions for the input variables.
Audit Metadata