ai-engineering

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly describes processing and "scrapes URLs" as part of context assembly (references/context-engineering.md) and defines web-search/tool-calling patterns such as a "search_web" tool schema (references/agentic-system-design.md), so it fetches untrusted public web content and injects it into the agent's prompt/context where that content can influence tool selection and downstream actions.