agent-registry
Warn
Audited by Snyk on Sep 5, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The agent registry skill interacts with the Agent Arena API to search, register, compare, and hire autonomous agents. While searching and comparing services returns descriptions and details from various third-party agents registered on-chain, the agent must actively query or search for specific items rather than ingesting an unselected, unvetted outsider stream.
MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).
- Direct money access detected (high risk: 1.00). The skill documentation explicitly incorporates cryptographic payment execution capabilities using the x402 protocol, specifically utilizing EIP-3009
transferWithAuthorizationfor signing and executing USDC payments on-chain. It includes TypeScript code examples that import private keys and set up automated transaction signing and payment flows via the@x402/coreand@x402/evmlibraries to pay for agent services and registry actions.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W009
MEDIUMDirect money access capability detected (payment gateways, crypto, banking).
Audit Metadata