vueuse-core-skilld

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly instructs the agent to consult bundled, user-generated GitHub discussions and public docs (see SKILL.md with References -> ./references/discussions/_INDEX.md and files like references/discussions/discussion-4091.md), so the agent will read and act on untrusted third-party content that can influence decisions and tool use.