ship
Warn
Audited by Snyk on Mar 5, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 1.00). The skill explicitly instructs the agent to "Fetch" other skill documents at runtime (e.g., https://ethskills.com//SKILL.md), meaning external content from that URL would be loaded during execution and could directly control prompts/instructions.
MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).
- Direct money access detected (high risk: 1.00). This skill is explicitly about building and deploying blockchain dApps that handle tokens, swaps, vaults, lending, and payments. It references concrete crypto primitives and integrations (ERC-20/ERC-721/ERC-4626, SafeERC20, OpenZeppelin, Uniswap/Aerodrome, Aave), wallet flows ("Approve → Execute", multisig / Gnosis Safe), swaps and gas costs, payment contracts (x402), and onchain transfers. Those are specific crypto/blockchain financial capabilities (wallets, swaps, signing, token transfers and deployments) rather than generic tooling. Therefore it grants direct crypto financial execution capability.
Audit Metadata