fuzzgpt
Skill2 starsChanged 7 days agoNo licenceView on GitHub
Use when you want to fuzz any software target — library, compiler, interpreter, parser, kernel/syscall, DB engine, SMT solver, binary/file format, or network protocol — by priming an LLM with that target's HISTORICAL bug-triggering code to generate unusual, edge-case inputs (history-driven LLM fuzzing). FuzzGPT-derived: retrieval replaces fine-tuning (Deng et al., arXiv:2304.02014): mine bug reports → auto-label each snippet's buggy fuzz target → few-shot / zero-shot / retrieval generation → crash + differential oracles. Trigger on "FuzzGPT", "fuzz this library/compiler/parser/protocol", "generate edge-case test programs", "history-driven fuzzing", or when pairing with vuln-research to turn a target's bug history into fresh fuzzing inputs. Target-agnostic: the "fuzz target" is whatever unit you point generation at — an API in the paper's DL study, but equally a compiler flag, SQL feature, syscall, opcode, or protocol field.
In this repository80 other files it gives its agents.
- agentic-spec-driven-developmentSkill
- bugbounty-poc-video-runnerSkill
- bug-bounty-reportingSkill
- codeqlSkill
- cookSkill
- ctfdSkill
- debateSkill
- evaluating-enhancing-vulnerability-reasoningSkill
- feature-engineeringSkill
- glitchtipSkill
- go-algorithmsSkill
- go-api-designSkill
- go-concurrencySkill
- go-idiomaticSkill
- go-stdlibSkill
- go-system-designSkill
- go-tddSkill
- hermes-mr-watchSkill
- hermes-self-evolutionSkill
- jevSkill
- joernSkill
- llm-domain-speedrunSkill
- oauth-auditSkill
- obsidian-spaced-repetitionSkill
- ofeliaSkill
- opengrep-rule-creatorSkill
- parallel-searchSkill
- photon-geocoderSkill
- python-algorithmsSkill
- python-api-designSkill
- python-concurrencySkill
- python-exploitationSkill
- python-idiomaticSkill
- python-performanceSkill
- python-stdlibSkill
- python-system-designSkill
- python-tddSkill
- react-components-typescriptSkill
- react-hooks-stateSkill
- react-performanceSkill
- react-server-dataSkill
- react-testing-a11ySkill
- refurbisherSkill
- rust-algorithmsSkill
- rust-api-designSkill
- rust-concurrencySkill
- rust-guidelinesSkill
- rust-idiomaticSkill
- rust-macrosSkill
- rust-performanceSkill
- rust-safetySkill
- rust-tddSkill
- rust-type-diagnosticsSkill
- rust-wasmSkill
- scrape-code-vulnerability-corpusSkill
- security-fix-oracleSkill
- sink-research-orchestratorSkill
- skill-smell-checkerSkill
- skillsmp-searchSkill
- ssrf-testingSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.