agent-native

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

• Third-party content exposure detected (high risk: 0.80). The skill's required workflow and reference files (e.g., references/agent-ui-communication.md and references/core-principles.md, plus references/files-and-context.md showing sources like sources/wikipedia.md) explicitly instruct agents to "find source materials," "download full text," and "search for and summarize sources," which indicates the agent ingests public third‑party web content and uses it to drive decisions and tool actions.