Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/ZealynxSecurity/kraitnpx agentmods add skills/zealynxsecurity/krait/fuzzerWrote 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/zealynxsecurity/krait/fuzzer)<a href="https://agentmods.dev/skills/zealynxsecurity/krait/fuzzer"><img src="https://agentmods.dev/badge/skills/zealynxsecurity/krait/fuzzer/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/zealynxsecurity/krait/fuzzer"><img src="https://agentmods.dev/badge/skills/zealynxsecurity/krait/fuzzer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00000 | $0.01554 |
| Opus 5.5 | $0.00000 | $0.00622 |
| Sonnet 5.5 | $0.00000 | $0.00311 |
| Haiku 4.5 | $0.00000 | $0.00155 |
Grade A, and why
fuzzer 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Krait Fuzzer — Invariant Extraction & Testing Methodology
This skill defines how to extract invariants from smart contracts and generate Foundry fuzz tests to verify them.
Core Principle
The LLM does NOT audit for vulnerabilities. It:
- Understands the code deeply
- Documents all invariants (properties that must always hold)
- Generates Foundry tests to verify those invariants
- Iterates on test failures to distinguish test bugs from real violations
Invariant Categories
| Category | Description | Example |
|---|---|---|
| accounting | Balance/supply consistency | totalSupply == sum(balances[i]) |
| access-control | Permission boundaries | onlyOwner can call pause() |
| state-transition | Valid state machine flows | state can only go ACTIVE → PAUSED → ACTIVE |
| economic | Price/rate/value bounds | exchangeRate >= 1e18 (never decreases) |
| token-conservation | No token creation/destruction | tokensBefore + deposited == tokensAfter |
| ordering | Temporal constraints | withdrawTime > depositTime |
| bounds | Value range constraints | fee <= MAX_FEE |
| relationship | Multi-variable relationships | debt <= collateral * ltv / 1e18 |
Invariant Extraction Methodology
Step 1: State Variable Analysis
For each contract:
- List ALL storage variables
- Group related variables (e.g.,
totalSupplyandbalancesmapping) - Identify computed relationships: does variable A depend on variable B?
- Check constructor/initializer: what invariants are established at deployment?
Step 2: Require/Assert Mining
Every require() and assert() is a developer-stated invariant:
require(balances[msg.sender] >= amount, "insufficient"); // INV: balance >= withdrawal
assert(totalSupply == _computeTotal()); // INV: supply consistency
Also check modifiers — onlyOwner, whenNotPaused, nonReentrant all encode invariants.
Step 3: Function-Level Invariants
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.
- 1mo ago First seen · 222 lines · 0 tokens per session scan A 95c3685662c3
fuzzer is a skill published in the GitHub repository ZealynxSecurity/krait (25 stars, last pushed 22d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,554 tokens. 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.
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.
playground
Interactively test any ChainGPT API endpoint. Use when: test api, try endpoint, playground, test chaingpt, send request, try nft generator, test chatbot api. Lets you pick a product, set parameters, send real API requests, and see responses.
analyzing-ethereum-smart-contract-vulnerabilities
A security-analysis guide for Solidity smart contracts, which are programs that run on the Ethereum blockchain. It uses Slither and Mythril to inspect contract code and execution paths for vulnerabilities.
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.
solidity-testing
Every core function must have tests covering.