Fizz
pashov/skills
Generate Echidna/Medusa-compatible Solidity fuzz suites from Foundry or Hardhat projects.
Operate AFL++, libFuzzer with Clang sanitizers, and Jazzer for advanced coverage-guided native and JVM fuzzing.
Install Operate Native Fuzzing
$ npx skills add cyberful/cyberful --skill operate-native-fuzzing -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install cyberful/cyberful operate-native-fuzzing --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/cyberful/cyberful.git skills-src && mkdir -p .claude/skills && cp -r skills-src/cyberful/builtin/skills/operate-native-fuzzing .claude/skills/operate-native-fuzzing && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "operate-native-fuzzing" agent skill from https://github.com/cyberful/cyberful/tree/main/cyberful/builtin/skills/operate-native-fuzzing into .claude/skills/operate-native-fuzzing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "operate-native-fuzzing", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/cyberful/cyberful/tree/main/cyberful/builtin/skills/operate-native-fuzzingType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add cyberful/cyberful --skill operate-native-fuzzing -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install cyberful/cyberful operate-native-fuzzing --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cyberful/cyberful.git skills-src && mkdir -p .agents/skills && cp -r skills-src/cyberful/builtin/skills/operate-native-fuzzing .agents/skills/operate-native-fuzzing && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "operate-native-fuzzing" agent skill from https://github.com/cyberful/cyberful/tree/main/cyberful/builtin/skills/operate-native-fuzzing into .agents/skills/operate-native-fuzzing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "operate-native-fuzzing", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add cyberful/cyberful --skill operate-native-fuzzing -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install cyberful/cyberful operate-native-fuzzing --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cyberful/cyberful.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/cyberful/builtin/skills/operate-native-fuzzing .cursor/skills/operate-native-fuzzing && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "operate-native-fuzzing" agent skill from https://github.com/cyberful/cyberful/tree/main/cyberful/builtin/skills/operate-native-fuzzing into .cursor/skills/operate-native-fuzzing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "operate-native-fuzzing", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/cyberful/cyberful.git --path cyberful/builtin/skills/operate-native-fuzzing--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add cyberful/cyberful --skill operate-native-fuzzing -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install cyberful/cyberful operate-native-fuzzing --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cyberful/cyberful.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/cyberful/builtin/skills/operate-native-fuzzing .gemini/skills/operate-native-fuzzing && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "operate-native-fuzzing" agent skill from https://github.com/cyberful/cyberful/tree/main/cyberful/builtin/skills/operate-native-fuzzing into .gemini/skills/operate-native-fuzzing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "operate-native-fuzzing", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install cyberful/cyberful operate-native-fuzzingInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add cyberful/cyberful --skill operate-native-fuzzing -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/cyberful/cyberful.git skills-src && mkdir -p .github/skills && cp -r skills-src/cyberful/builtin/skills/operate-native-fuzzing .github/skills/operate-native-fuzzing && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "operate-native-fuzzing" agent skill from https://github.com/cyberful/cyberful/tree/main/cyberful/builtin/skills/operate-native-fuzzing into .github/skills/operate-native-fuzzing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "operate-native-fuzzing", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add cyberful/cyberful --skill operate-native-fuzzing -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install cyberful/cyberful operate-native-fuzzing --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cyberful/cyberful.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/cyberful/builtin/skills/operate-native-fuzzing .opencode/skills/operate-native-fuzzing && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "operate-native-fuzzing" agent skill from https://github.com/cyberful/cyberful/tree/main/cyberful/builtin/skills/operate-native-fuzzing into .opencode/skills/operate-native-fuzzing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "operate-native-fuzzing", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
operate-native-fuzzing- GitHub stars
- 135
- Token cost
- ~1.3k tokens
- SKILL.md length
- 557 words
- Files
- 3 (incl. references)
- Skills in repo
- 85
- Repo updated
- First seen
- Licence
- AGPL-3.0
At a glance
Operate AFL++, libFuzzer with Clang sanitizers, and Jazzer for advanced coverage-guided native and JVM fuzzing.
- Designing harnesses
- SKILL.md covers Write the harness contract, Choose the engine deliberately, Build the instrumentation matrix and Seed for grammar and state, plus 3 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
- Constructing and minimizing corpora
What it does
Operate Native Fuzzing is an agent skill from cyberful/cyberful. Operate AFL++, libFuzzer with Clang sanitizers, and Jazzer for advanced coverage-guided native and JVM fuzzing. Use when designing harnesses, constructing and minimizing corpora, diagnosing coverage plateaus, selecting sanitizers or instrumentation modes, fuzzing parsers and state machines, deduplicating crashes, or turning audit hypotheses into deterministic regression cases.
Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `agents/openai.yaml` and `references/fuzzing-fieldbook.md`).
It sits in Security, covering Fuzzing. The repository describes itself as: Cyberful is an open-source AI Red Team for discovering, exploiting, verifying, and remediating vulnerabilities. The licence is AGPL-3.0.
When your agent uses it
- Designing harnesses
- Constructing and minimizing corpora
- Diagnosing coverage plateaus
- Selecting sanitizers
Example prompts
- “/operate-native-fuzzing”
What it can do on your machine
Read from SKILL.md and the folder at commit ec598a6. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Operate Native Fuzzing loads about 1.3k tokens when it runs, and up to ~2k if it reads all its reference files. Until then it costs about 101 tokens; SKILL.md has 557 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from cyberful/cyberful at commit ec598a6, republished under its AGPL-3.0 licence (© cyberful). 557 words, ~1,302 tokens.
Download SKILL.mdSave it as
.claude/skills/operate-native-fuzzing/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.- name
- operate-native-fuzzing
- description
- Operate AFL++, libFuzzer with Clang sanitizers, and Jazzer for advanced coverage-guided native and JVM fuzzing. Use when designing harnesses, constructing and minimizing corpora, diagnosing coverage plateaus, selecting sanitizers or instrumentation modes, fuzzing parsers and state machines, deduplicating crashes, or turning audit hypotheses into deterministic regression cases.
- metadata.domain
- native-security
- metadata.subdomain
- coverage-guided-fuzzing
- metadata.triggers
- native fuzzing campaign, libfuzzer harness, afl++ campaign, jazzer fuzzing, sanitizer crash triage, corpus minimization
- metadata.tags
- aflplusplus, libfuzzer, jazzer, sanitizers, corpus, crash-triage
Operate Native Fuzzing
The harness defines the reachable security model. Optimize semantic depth and reproducibility before execution speed; a fast harness that never crosses initialization, checksum, or parser state boundaries produces false assurance efficiently.
Write the harness contract
Document target function and build, input framing, state reset, environment, allocator, thread model, timeout, maximum input, expected rejects, external side effects, and invariants. Remove network, clock, randomness, process-global caches, and nondeterministic concurrency unless they are the property under test.
For structured formats, expose bytes at the earliest production parser boundary while retaining real downstream validation and object use. Do not replace the parser with a fuzzer-specific decoder that cannot represent production bugs. Validate source harness syntax and ABI with harness_validate; compile opaque production types against their real headers instead of guessing their size or layout.
Choose the engine deliberately
- Use libFuzzer for in-process C/C++ targets with tight sanitizer and coverage integration.
- Use AFL++ when fork/persistent modes, binary-only modes, distributed queues, custom mutators, CmpLog, or file/process harnesses fit better.
- Use Jazzer for JVM targets, Java/Kotlin parsers, and sanitizer hooks for injection/deserialization-style behavior.
Read references/fuzzing-fieldbook.md for harness diagnostics and plateau recovery.
Use fuzz_campaign start for a phase-owned background campaign, then status, coverage, and crashes instead of launching an untracked daemon. Create a checkpoint before handoff. Use pause, resume, and stop for lifecycle control; the bridge reaps any surviving process when the phase closes.
Build the instrumentation matrix
Create reproducible debug symbols and separate ASan/UBSan, MSan where the whole dependency graph supports it, and coverage-focused builds. Treat sanitizer incompatibilities and optimized release-only behavior explicitly. For native code reached through JVM/JNI, fuzz and symbolize both sides.
Compile AFL++ targets with afl-clang-fast or afl-clang-fast++, and libFuzzer targets with Clang plus fuzzer and sanitizer flags. Keep raw compiler invocations in evidence.
Seed for grammar and state
Start with valid minimal examples spanning format versions, optional sections, boundary sizes, encodings, compression, nested structures, and semantic states. Minimize only after confirming that rare states and coverage are retained. Add dictionaries for tokens; use custom mutators when checksums, length fields, or dependent structures block progress.
Show full SKILL.md (213 more words)Show less
Diagnose plateaus
Measure executions, edge/feature growth, corpus growth, reject-stage distribution, input length, stability, and time per seed. Instrument milestones inside the harness or target. Apply comparison tracing/CmpLog, value profiles, dictionaries, corpus surgery, targeted seeds, state snapshots, or a better boundary based on the blocking predicate.
Triage and prove crashes
Reproduce outside the fuzzer with the exact build and environment; minimize while preserving the same root cause; symbolize; identify first invalid state rather than final crash; deduplicate by causal frame/data invariant; test sanitizer-independent behavior where relevant; and create a regression case.
Use crash_triage for reproduction, symbolization, classification, deduplication, minimization, and evidence export. A campaign crash list is discovery evidence, never a confirmed vulnerability.
Keep transport success, fuzzing runner status, target-process exit, sanitizer observation, and infrastructure failure as distinct facts. Preserve the raw target exit and sanitizer output as primary evidence; runner summaries and ad hoc classifiers are derived evidence and cannot silently override it. Prefer crash_triage over a custom classifier when the operation fits its contract, and record any disagreement against the hypothesis oracle explicitly.
Deliver
Preserve source/build hash, compiler, flags, harness, corpus provenance, engine configuration, coverage and stability metrics, crash input, minimized reproducer, sanitizer log, root-cause trace, and untested state space. "No crashes" is only meaningful with the harness and coverage evidence attached.
© cyberful, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 2 other files (references) in cyberful/builtin/skills/operate-native-fuzzing of cyberful/cyberful.
- SKILL.md
- agents/openai.yaml
- references/fuzzing-fieldbook.md
Open the folder on GitHubat commit ec598a6
Compare with similar skills
Operate Native Fuzzing next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Operate Native Fuzzing this skillcyberful/cyberful | 135 | — | ~1.3k | Automated safety check: Pass | AGPL-3.0 | |
| Fizzpashov/skills | 1.2k | 2 repos | ~11k | Automated safety check: Pass | MIT | |
| Fizz Syncpashov/skills | 1.2k | 2 repos | ~3.9k | Automated safety check: Pass | MIT | |
| Research FuzzerARA-Labs/Agent-Native-Research-Artifact | 692 | — | ~2.4k | Automated safety check: Pass | MIT | |
| Vuln Researchtanweai/xianzhi-research | 185 | — | ~847 | Automated safety check: Pass | None | |
| Binary Reverse Engineering Audittihanyin/REx-skill | 108 | — | ~5.1k | Automated safety check: Pass | MIT |
Similar skills
Fizz Sync
pashov/skills
Reconcile an existing Fizz harness with a changed source tree.
Research Fuzzer
ARA-Labs/Agent-Native-Research-Artifact
Treat an open-ended investigation the way a fuzzer treats a program.
Vuln Research
tanweai/xianzhi-research
安全研究元思考方法论 - 从先知社区5600+篇安全文档中提炼的漏洞挖掘方法论框架. An agent skill from tanweai/xianzhi-research.
Binary Reverse Engineering Audit
tihanyin/REx-skill
Guides evidence-first reverse engineering of compiled programs to find and prove defects, from triage and decompilation to fuzzing, patch diffing and firmware.
Harness Design Fuzzing
provos/ironcurtain
Reference vocabulary for designing instrumented harnesses that drive vulnerability discovery — design classes (trigger-driven vs coverage-driven), tiered scope (T1 isolated function / T2…
More from cyberful/cyberful
All 85 skills in this repoAudit Infrastructure As Code
cyberful/cyberful
Audit infrastructure-as-code artifacts for unsafe defaults, policy gaps, privilege exposure, control drift, and deployment-impact evidence.
Audit Kubernetes Policy Enforcement
cyberful/cyberful
Audit Kubernetes admission and policy-as-code enforcement against local workload manifests, exception paths, namespace scope, and deployment evidence.
Audit Pci Dss Penetration Test Evidence
cyberful/cyberful
Audit PCI DSS penetration-test methodology, scope, internal and external reports, segmentation results, tester independence, remediation, retesting, retention, and multi-tenant support evidence.
Operate Content Discovery
cyberful/cyberful
Design and interpret advanced content discovery with ffuf and complementary web fuzzers.
Operate Network Recon
cyberful/cyberful
Build a high-fidelity network and service inventory using Nmap, Masscan, packet capture, DNS, and protocol-specific follow-up.
Operate Sast Toolchain
cyberful/cyberful
Operate Semgrep and source-oriented static analysis as a hypothesis, coverage, and regression system during advanced code audits.
Related
Categories
Questions about Operate Native Fuzzing
What does Operate Native Fuzzing do?
Operate AFL++, libFuzzer with Clang sanitizers, and Jazzer for advanced coverage-guided native and JVM fuzzing. Operate Native Fuzzing is an agent skill from cyberful/cyberful. Operate AFL++, libFuzzer with Clang sanitizers, and Jazzer for advanced coverage-guided native and JVM fuzzing.
When should I use Operate Native Fuzzing?
Operate Native Fuzzing fits situations like: designing harnesses; constructing and minimizing corpora; diagnosing coverage plateaus; selecting sanitizers.
How do I install Operate Native Fuzzing in Claude Code?
Run `npx skills add cyberful/cyberful --skill operate-native-fuzzing -a claude-code`. Or copy the skill folder (cyberful/builtin/skills/operate-native-fuzzing in cyberful/cyberful) into .claude/skills/operate-native-fuzzing in your project. Claude Code loads it when a task matches its description.
How do I install Operate Native Fuzzing in Codex?
Run `npx skills add cyberful/cyberful --skill operate-native-fuzzing -a codex`. Or copy the skill folder (cyberful/builtin/skills/operate-native-fuzzing in cyberful/cyberful) into .agents/skills/operate-native-fuzzing in your project. Codex loads it when a task matches its description.
Can I use Operate Native Fuzzing in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add cyberful/cyberful --skill operate-native-fuzzing -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/operate-native-fuzzing, .gemini/skills/operate-native-fuzzing, .github/skills/operate-native-fuzzing and .opencode/skills/operate-native-fuzzing in your project.
What does Operate Native Fuzzing need to run?
SKILL.md names no scripts, command-line tools or credentials: Operate Native Fuzzing is instructions for the agent only.
Does Operate Native Fuzzing access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Operate Native Fuzzing safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Operate Native Fuzzing use?
Operate Native Fuzzing is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Operate Native Fuzzing use?
About 1.3k tokens (SKILL.md is roughly 5.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 729 tokens, read only when the agent opens those files.
What are the alternatives to Operate Native Fuzzing?
Skills that share tags, products or a category with Operate Native Fuzzing: Fizz (pashov/skills, 1.2k stars), Fizz Sync (pashov/skills, 1.2k stars), Research Fuzzer (ARA-Labs/Agent-Native-Research-Artifact, 692 stars) and Vuln Research (tanweai/xianzhi-research, 185 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Operate Native Fuzzing?
cyberful (a GitHub organization) maintains it in cyberful/cyberful, which has 135 GitHub stars. The repository holds 85 skills in this directory. The repository was last updated on August 24, 2026.
Source: cyberful/cyberful on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.