firewall-review

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill's output format and "required evidence" explicitly ask the agent to include specific configuration snippets or policy text as evidence, which can contain secrets, and there is no instruction to redact or avoid printing those secret values, so the LLM may be required to output secrets verbatim.

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

• Third-party content exposure detected (medium risk: 0.30). SKILL.md specifies the skill is auto-invoked to audit firewall configurations by globbing/grepping the user-supplied target-file-or-directory and processing configuration comments/rule descriptions as untrusted data.