菜单
Security-focused review for Hyperlane protocol code. Use for Solidity contracts, Rust agents, and infrastructure changes.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Update standing fee quotes for the CROSS/moonpay warp route. Use when asked to set, update, or change fees/bps for specific chains, tokens, or directions in the MoonPay route. Also use when asked to show or read current standing quotes.
Encode and decode raw Hyperlane messages to/from packed hex bytes using the CLI. Use when you need to construct a message for testing, inspect a raw message from logs or a transaction, or decode a warp transfer body.
Helper skill for using Hyperlane CLI address conversion utilities (addressToBytes32 and bytes32ToAddress) for cross-chain message formatting
A skill that allows a user to validate that a warp route deployment will be in the expected state after applying some configuration
Simulate pending Safe (multisig) governance txs for a warp route by replaying the literal calldata onto anvil forks, self-relaying any ICA messages, then running warp check against the desired registry config. Use to verify that a not-yet-signed Safe batch produces the intended warp route config before signing.
Add a new chain to an existing warp route owned by a customer. Reads a Linear ticket, adds the new chain to the deploy.yaml, builds a customer-specific strategy file for existing chains, runs warp apply, and outputs transaction files for the customer to sign via their multisig.
| name | claude-security-review |
| description | Security-focused review for Hyperlane protocol code. Use for Solidity contracts, Rust agents, and infrastructure changes. |
Use this skill for security-focused code review of Hyperlane protocol code.
Read and apply the security guidelines from .github/prompts/security-scan.md to review the code changes.
Report findings with severity ratings (Critical/High/Medium/Low/Informational) and suggested fixes.
When reviewing a PR, deliver feedback as a single consolidated GitHub review using /inline-pr-comments. Each run produces a separate review. The skill fetches prior reviews/comments for context — avoid duplicating previously raised issues.
