terraform-module-creator
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill acts on user requests regarding Terraform configurations and has access to execute shell commands. This creates a surface for indirect prompt injection if the data being processed contains malicious instructions.
- Ingestion points: Processes user queries and potential file content via
ReadandGreptools (SKILL.md). - Boundary markers: The instructions do not define delimiters or specific warnings to ignore instructions embedded within the processed data.
- Capability inventory: The skill is configured with access to
Bash(cmd:*),Write, andEdittools, allowing for significant system interaction (SKILL.md). - Sanitization: There is no evidence of input validation or sanitization routines for the data processed by the agent.
Audit Metadata