iac-security

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly requires including "Evidence: " in findings and instructs scanning state files (e.g., terraform.tfstate), which would cause the LLM to reproduce literal code lines that may contain secrets verbatim.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.75). The required runtime workflow ingests the target IaC files’ string values/comments (which can be outsider-authored, e.g., PR/issue/wiki content or downloaded attachments) into the LLM context for analysis, creating an indirect prompt-injection risk from that free text.