auditing-wallet-security

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

• Third-party content exposure detected (high risk: 1.00). This skill fetches and interprets public, third-party blockchain and block-explorer data (e.g., eth_getLogs/eth_call to public RPCs and Etherscan/BSCScan/PolygonScan APIs as used in scripts/approval_scanner.py and scripts/tx_analyzer.py and declared in SKILL.md/ARD.md), and those untrusted responses (token/contract names, verification status, logs) are used directly to determine risk scores and revoke recommendations, so external content can materially influence agent behavior.