sybil-detection

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

• Third-party content exposure detected (high risk: 1.00). The skill's workflow and scripts (e.g., SKILL.md and scripts/detect_sybils.py / scripts/funding_tracer.py) explicitly fetch and ingest public on‑chain data from third‑party sources such as the Helius API (https://api.helius.xyz/...), Solana RPC endpoints (getTokenLargestAccounts/getSignaturesForAddress), and SolanaTracker/DexScreener, and then directly use that untrusted, user-generated transaction/holder data to drive clustering, scoring, and detection decisions.