wasm-gallery

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

• Third-party content exposure detected (high risk: 0.75). The required workflow involves browsing/searching/installing from a “community gallery,” which at runtime will fetch and ingest outsider-authored agent descriptions/configuration text from a public/community source into the agent’s LLM context via the mcp__claude-flow__wasm_gallery_list/search and subsequent mcp__claude-flow__wasm_agent_create steps.