terraform-patterns
Pass
Audited by Gen Agent Trust Hub on Apr 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted user-provided Terraform (.tf) files, creating a surface for indirect prompt injection. \n
- Ingestion points: The skill workflow in SKILL.md (commands /terraform:review and /terraform:security) instructs the agent to read all .tf files within a target directory and analyze their content. \n
- Boundary markers: Absent. The instructions do not provide delimiters or clear warnings to the agent to ignore any natural language instructions that might be embedded within the Terraform code, comments, or strings. \n
- Capability inventory: The skill workflow includes command execution (python3 scripts/tf_module_analyzer.py and python3 scripts/tf_security_scanner.py) and file system read access to process the user infrastructure code. \n
- Sanitization: Absent. The agent is instructed to read raw file content from the workspace and use it to generate reports and run analysis scripts without prior validation or escaping of the input data.
Audit Metadata