conflux-scan-rpc

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

• Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md and api-endpoints.md explicitly instruct the agent to fetch and parse public ConfluxScan API and RPC endpoints (e.g., https://evmapi-testnet.confluxscan.org and https://evmtestnet.confluxrpc.com for getabi/getsourcecode and RPC calls), which are open third-party sources of user-provided contract ABI/source that the agent must read and can materially influence analysis and subsequent actions.