solana-clustering-case-study-agent

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

• Third-party content exposure detected (high risk: 0.90). The skill's workflow explicitly requires verifying claims against public on-chain data and anchoring evidence on explorer URLs (e.g., Solscan, SolanaFM) and indexer/RPC queries as part of case construction, so the agent is expected to ingest and act on untrusted public third‑party content from explorers/indexers.