competitive-landscape

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

• Third-party content exposure detected (medium risk: 0.30). The Competitive Landscape workflow explicitly instructs the agent to do “fresh web research: crypto Twitter, GitHub, DeFiLlama, app directories” (and to search solana-new ecosystem catalogs), which will cause the LLM to ingest outsider-authored free text from those community/feed sources and repositories at runtime.