tanstack-ai-vue-skilld

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

• Third-party content exposure detected (high risk: 0.90). The skill's documentation (e.g., references/docs/adapters/anthropic.md and references/docs/adapters/gemini.md) explicitly documents provider tools like webFetchTool, urlContextTool, and googleSearchTool that let the agent fetch and ingest arbitrary public URLs and search results so the model reads third‑party web/forum content as part of its workflow, which can materially influence tool use and decisions.