Menu
Security vulnerability analysis for Solidity smart contracts. Runs static analysis, optional dynamic testing and formal verification.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
End-to-end protocol build pipeline — contract development, testing, auditing, gas optimization, deployment, and dApp integration. Hybrid sequential/parallel execution.
Shows all available eth-agents skills with trigger phrases and usage examples.
Extracts a reusable skill pattern from the current session and saves it to user scope for automatic activation in future sessions.
Full contract build pipeline — write → TDD loop → static audit → gas optimization. Produces a production-ready contract.
Multichain smart contract deployment with Etherscan verification. Requires explicit user confirmation before mainnet execution.
Mainnet fork testing for smart contracts. Tests against real on-chain state at a pinned block number.
| name | audit |
| description | Security vulnerability analysis for Solidity smart contracts. Runs static analysis, optional dynamic testing and formal verification. |
| triggers | ["audit this contract","audit this","check for vulnerabilities","security review","find bugs in","analyze security","is this contract safe"] |
| flags | ["--static: auditor only (default, ~2 min)","--dynamic: + fork tests and fuzz campaigns","--formal: + formal verification (Certora/Halmos/Echidna)","--full: all three in sequence"] |
| agent | orchestrator |
| model | opus |
Runs a security audit pipeline on smart contracts in the current project. Depth is configurable from fast static analysis to full formal verification.
Default depth is --static. User can specify depth in natural language: "do a full audit", "just a quick static check", "run formal verification".
eth_skill_start({ skill: "audit", totalPhases: 1 })auditor with the requested depth flag--dynamic or --full: auditor spawns → orchestrator spawns integration-test-engineer with audit findings as context--formal or --full: orchestrator presents tool options to user → spawns security-specialistaudit-report.mdeth_reset()# Natural language invocations:
"audit this contract" → --static (default)
"do a full security audit" → --full
"check for reentrancy vulnerabilities" → --static with focus hint
"run formal verification on the vault" → --formal
# Output:
audit-report.md — findings sorted by severity with remediation suggestions
Depth is detected from user intent:
--static--dynamic--formal--full--static