address-pr-comments

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

• Third-party content exposure detected (high risk: 0.85). The skill’s runtime workflow includes “Fetch all three comment sources” and then “Present the plan” with the Comment text; those sources include outsider-authored PR comment bodies (e.g., other reviewers’ comments on the PR) that are ingested as readable text into the agent context for classification/planning.