aws-review

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill explicitly instructs the agent to locate and include configuration files such as .aws/credentials and to provide "evidence" as specific configuration or code snippets, which can force the LLM to reproduce secret values verbatim in its output if present.

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

• Third-party content exposure detected (medium risk: 0.30). SKILL.md’s runtime workflow discovers and reads IaC/config files from the target repository (via Glob/allowed file tools and the provided “target-file-or-directory” argument), so outsider-authored free text can be ingested through those Terraform/CloudFormation/policy file contents.