receiving-code-review

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

• Third-party content exposure detected (high risk: 0.85). The skill’s workflow is about handling “External Reviewers” feedback, which at runtime would typically be sourced from outsider-authored review comments/PR discussion text (e.g., GitHub issue/PR comment bodies) that the agent reads and incorporates into the LLM context to “READ: Complete feedback.”