terraform-module-creator
Fail
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: HIGHCOMMAND_EXECUTIONNO_CODEPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION] (HIGH): The skill requests permission to use the 'Bash' tool. Given the skill's purpose involves infrastructure-as-code (Terraform), this allows for arbitrary shell command execution which can lead to system compromise.
- [NO_CODE] (INFO): The skill contains no functional scripts or prompt logic, consisting only of metadata and descriptive markdown. This forces the agent to rely on its base training without specific security constraints for the requested tools.
- [PROMPT_INJECTION] (HIGH): This skill is highly vulnerable to indirect prompt injection due to its capabilities. 1. Ingestion points: User requests via triggers like 'terraform module creator' and likely existing Terraform files on the system. 2. Boundary markers: Absent; no delimiters or instructions to ignore embedded commands are provided. 3. Capability inventory: Includes 'Bash', 'Write', and 'Edit' which allow for filesystem changes and system-level execution. 4. Sanitization: Absent; no validation or filtering of input data is defined. Maliciously crafted requests or infrastructure files could lead to the execution of unintended commands.
Recommendations
- AI detected serious security threats
Audit Metadata