Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Awarexone/web3-bug-bounty-hunting-ai-skills --skill web3-hunt-zksync-eragit clone --depth 1 https://github.com/Awarexone/web3-bug-bounty-hunting-ai-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/awarexone/web3-bug-bounty-hunting-ai-skills/web3-hunt-zksync-era)<a href="https://agentmods.dev/skills/awarexone/web3-bug-bounty-hunting-ai-skills/web3-hunt-zksync-era"><img src="https://agentmods.dev/badge/skills/awarexone/web3-bug-bounty-hunting-ai-skills/web3-hunt-zksync-era/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/awarexone/web3-bug-bounty-hunting-ai-skills/web3-hunt-zksync-era"><img src="https://agentmods.dev/badge/skills/awarexone/web3-bug-bounty-hunting-ai-skills/web3-hunt-zksync-era.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Rogue Agent · line 99 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00088 | $0.02333 |
| Opus 5 | $0.00044 | $0.01167 |
| Sonnet 5 | $0.00018 | $0.00467 |
| Haiku 4.5 | $0.00009 | $0.00233 |
Grade A, and why
web3-hunt-zksync-era scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- web3-hunt-zksync-era — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LIVE HUNT: ZKsync Era (Immunefi) — COMPLETED, 0 FINDINGS
Outcome: 0 submittable findings after 5+ sessions, 22+ agents, 25+ contracts, 25+ attack vectors Lesson: This file exists as a DEFENSE STUDY — what a hardened protocol looks like, and when to stop hunting.
TARGET PROFILE
| Field | Value |
|---|---|
| Protocol | ZKsync Era (L2 rollup) |
| Platform | Immunefi |
| TVL | $322M (L2BEAT Total Value Secured) |
| Bounty | $100K minimum Critical, $1.1M max |
| Codebase | 750K LOC (Solidity + Rust + Yul) |
| Audits | OpenZeppelin V29 (June 2025), multiple prior audits |
| Version | Protocol V29.4 |
| Repo | github.com/matter-labs/era-contracts |
| Primacy | Primacy of Impact — even out-of-scope assets qualify |
| Prior payouts | $50K (ChainLight ZK circuit bug) |
Pre-Dive Scorecard
| Check | Result | Score |
|---|---|---|
| TVL > $500K | $322M | PASS |
| Max payout > $10K | $100K minimum | PASS |
| Simple protocol? | 750K LOC, L1↔L2 bridge + ZK + governance | PASS (complex) |
| < 500 lines? | 750K LOC | PASS |
| Audit quality | OpenZeppelin (top-tier) on ALL critical paths | WARNING |
REFINEMENT: Pre-dive should weight audit quality MORE for large protocols. A protocol passing TVL/LOC/payout checks can still be unhuntable if OZ/ToB audited the exact code you'd hunt. Add "audit firm tier" as a SOFT kill signal for 500K+ LOC protocols.
ARCHITECTURE (What Makes It Hardened)
L1 Bridge Stack
Bridgehub (router)
├── L1AssetRouter (token routing)
│ ├── L1Nullifier (deposit/withdrawal state)
│ └── L1NativeTokenVault (token custody)
├── ChainTypeManager (chain registration)
└── ValidatorTimelock (RBAC execution delay)
L2 System Contracts (kernel space 0x8000-0xFFFF)
Bootloader (0x8001) → AccountCodeStorage, NonceHolder, KnownCodeStorage,
ImmutableSimulator, ContractDeployer, L1Messenger (0x8008),
MsgValueSimulator, L2BaseToken (0x800a), SystemContext (0x800b),
BootloaderUtilities, Compressor, ComplexUpgrader
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 179 lines · 88 tokens per session scan A 655bc7b69deb
web3-hunt-zksync-era is a skill published in the GitHub repository Awarexone/web3-bug-bounty-hunting-ai-skills (143 stars, last pushed 18d ago), licensed MIT. It adds 88 tokens to every session and 2,333 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
analyzing-ethereum-smart-contract-vulnerabilities
Perform static and symbolic analysis of Solidity smart contracts using Slither and Mythril to detect reentrancy, integer overflow, access control, and other vulnerability classes before deployment to Ethereum mainnet.
propfund
Trade on PropFund, the decentralized on-chain prop firm for AI agents. Two layers: PropFund SCREENS you (a free evaluation, then a virtual "funded" probation leg that builds an immutable on-chain record — pool-as-counterparty, no real firm capital), and AgentDesk PAYS you (once your record clears the bar you graduate…
token-antiflash
When this skill is triggered, DO NOT directly implement all strategies. Follow this workflow.
solidity-coding
When a contract involves state initialization (external addresses, business parameters, role assignments), DO NOT default to any single approach. Follow this workflow.
solidity-checklist
Most on-chain operation failures come from skipping systematic verification. Instead of the reactive loop.
programmable-v4-hook-builder
Build, repair, validate, submit, or track a complete Programmable Uniswap v4 Custom launch through the public V3 API. Use when the user names Programmable and wants implementation or launch work for a hook, token, multi-contract graph, app, game, service, or hybrid. Do not use for explanation-only questions, unrelated…