temporal

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

• Third-party content exposure detected (high risk: 0.90). The skill's references (notably references/ai-patterns.md and references/typescript-sdk.md) include concrete workflow/activity patterns that call out to external web content (e.g., an activities.fetchData(url) example, a "search_web" tool in TOOL_REGISTRY, and RAG pipelines that pass retrieved documents into LLM activities), meaning untrusted public third‑party content is fetched and then directly used to influence LLM decisions and workflow actions.