building-terraform-modules
Pass
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill promotes secure DevOps practices through its instructions and the
assets/validation_rules.jsonfile. The validation rules specifically target security risks like sensitive data in variable defaults (no_sensitive_data_in_defaults) and the use of risky provisioners (no_local_exec). - [INDIRECT_PROMPT_INJECTION]: The skill processes user-defined infrastructure specifications to generate HCL code and executes CLI tools such as
terraform validateandterraform-docs. This introduces a potential surface for indirect prompt injection if an attacker provides malicious module specifications designed to influence the agent's output or command execution. - Ingestion points: User-provided specifications for cloud resources, variable definitions, and module scope (SKILL.md).
- Boundary markers: No explicit delimiters or instructions are provided to the agent to treat user input as data only.
- Capability inventory: The skill has access to file system operations (
Write,Edit) and shell command execution (Bash(cmd:*)) as defined in the frontmatter (SKILL.md). - Sanitization: There are no specific sanitization steps described to validate or escape user-provided strings before they are incorporated into generated files or CLI commands.
Audit Metadata