eval-creator-ci

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

• Third-party content exposure detected (high risk: 0.70). The skill's create-mode workflow explicitly reads the "learning_aggregator_ci" workflow artifact or a "gap report issue comment" from GitHub (SKILL.md and references/workflow-example.md) and then automatically creates eval cases from that content, meaning untrusted user-generated artifacts or issue comments could directly influence CI actions.