NYC

erc-8004

Warn

Audited by Snyk on Feb 15, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). The skill's runtime scripts (notably get-agent.sh and the HTTP registration flow) fetch and display registration JSONs from arbitrary IPFS URIs and user-provided HTTPS URLs (via curl to gateway.pinata.cloud, ipfs.io, or any REGISTRATION_URL), meaning the agent will read and interpret untrusted, user-hosted third‑party content.

MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).

  • Direct money access detected (high risk: 1.00). The skill explicitly performs on-chain crypto operations: it includes scripts to "bridge ETH to mainnet", contract addresses, and a workflow step to "Register On-Chain" by calling register(agentURI) on the Identity Registry. The provided SDK example accepts a privateKey and rpcUrl (implying transaction signing) and the docs mention gas costs. These are specific crypto/blockchain capabilities (wallet signing, bridging, sending transactions) that can move value. Therefore it grants direct financial execution authority.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 08:32 PM