vue-skilld

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly includes and directs the agent to consult packaged community Q&A and discussion content under references/discussions/*.md (with URLs to https://github.com/orgs/vuejs/discussions/...), which are public, user-generated sources and are part of the skill's required reference workflow used for debugging and guidance, so those third‑party instructions could materially influence the agent's actions.