pinia-skilld

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

• Third-party content exposure detected (high risk: 0.80). The skill bundles and instructs the agent to consult public, user-generated discussion content (see references/discussions/*.md and the SKILL.md "References" section with multiple GitHub discussion URLs like https://github.com/vuejs/pinia/discussions/2889), so the agent will read/interpret untrusted third‑party forum content as part of its workflow which can materially influence actions and recommendations.