terraform-iac
Pass
Audited by Gen Agent Trust Hub on Mar 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to autonomously execute shell commands (
ls) to inspect the local filesystem for installed skills. This check probes multiple standard skill directories (e.g.,~/.claude/skills/,~/.agent/skills/) to identify which recommended companion skills are missing. - [EXTERNAL_DOWNLOADS]: The skill provides instructions to download and install additional resources using the
npx skills addcommand. These downloads target companion skills from the same vendor (AbsolutelySkilled) for managing cloud providers and CI/CD pipelines. - [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection. Because it processes and analyzes user-supplied Terraform HCL configurations, it could be coerced into following malicious instructions embedded in comments or metadata within those files.
- Ingestion points: Ingests and processes untrusted Terraform HCL code and documentation from the user's project (SKILL.md).
- Boundary markers: Lacks explicit instructions for the agent to disregard natural language instructions or comments found within the infrastructure code being processed.
- Capability inventory: The agent has the ability to execute Terraform CLI commands, read files, and write to the local filesystem.
- Sanitization: No specific sanitization or filtering of input data is defined before processing.
Audit Metadata