resonance-researcher

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to "Search: Gather raw data (Browser/Docs/Code)" and the LLMs.txt protocol requires curling and ingesting public /llms.txt and external documentation (e.g., hono.dev, drizzle links), meaning the agent will fetch and read untrusted public web content that could carry indirect prompt injection.