code-review-excellence

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

• Third-party content exposure detected (high risk: 0.85). This skill’s required workflow includes “Read PR description and linked issue”/“Review pull requests and code changes,” which at runtime would ingest outsider-authored free text from PR/issue bodies (and their comments) into the LLM context via the PR/issue text the agent is asked to read.