terraform-module-scaffolder
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- [Prompt Injection] (SAFE): No patterns of instruction override, jailbreaking, or system prompt extraction were found. The instructional language is benign and focused on scaffolding tasks.
- [Data Exposure & Exfiltration] (SAFE): There are no hardcoded credentials or sensitive file paths. No network operations (curl, wget, etc.) are present in the instructions.
- [Obfuscation] (SAFE): The text is clear and readable. No Base64 encoding, zero-width characters, or homoglyphs were detected.
- [Unverifiable Dependencies & RCE] (SAFE): The skill does not define any external package dependencies (Python/Node) or attempt to execute remote scripts.
- [Indirect Prompt Injection] (LOW): This category identifies the attack surface for untrusted user input.
- Ingestion points: The agent gathers requirements (module name, resources) directly from user input.
- Boundary markers: None. The skill assumes the user provides legitimate infrastructure requirements.
- Capability inventory: The skill is limited to generating/writing text files (.tf, .md) to the local filesystem.
- Sanitization: None specified. However, the risk is limited to generating invalid or malicious Terraform code that would require a separate user-initiated 'terraform apply' to have any side effects.
- [Persistence Mechanisms] (SAFE): No attempts to modify shell profiles, crontabs, or system services were found.
- [Dynamic Execution] (SAFE): The skill generates static code templates. It does not use unsafe deserialization or runtime code compilation techniques.
Audit Metadata