debug-program

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow explicitly tells the agent to fetch and interpret public blockchain data (e.g., simulate and read transaction logs/account state via connection.simulateTransaction/getTransaction, use surfpool with --rpc-url such as https://api.mainnet-beta.solana.com, and run solana logs), which are untrusted, user-generated third‑party sources whose contents directly drive debugging decisions and next actions.