azure-review

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill's output template and evidence requirements explicitly instruct the agent to include "specific configuration or code snippet" as evidence (and to read IaC files and Key Vault configs) without any instruction to redact secrets, which could force the LLM to reproduce secret values verbatim.

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

• Third-party content exposure detected (medium risk: 0.30). SKILL.md’s required runtime workflow reads Azure infrastructure-as-code configuration files (Terraform/Bicep/ARM/policy documents) from the provided repository/target via “Glob” discovery and evaluates their string values/comments as data.