tilegym-monkey-patch-kernels-to-transformers

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

• Third-party content exposure detected (high risk: 0.75). references/kernel-integration.md step 1 explicitly instructs explore subagents to use WebSearch/WebFetch (public web content) and then summarize/emit it into Definition/Solution metadata, which the agent will read and include in its LLM context—an indirect prompt-injection path from outsider-authored free text.