fuzzgpt skillA
fuzzgpt is agent-read markdown (skill) from lu1sdv/skillsmd: 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 → cra.
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# FuzzGPT — History-Driven LLM Fuzzing > **FuzzGPT-derived: retrieval replaces fine-tuning.** The original paper's FS and ZS > variants are reproduced faithfully. Fine-tuning (FT) is replaced by an > embedding-retrieval pathway (RT) — see `references/retrieval.md`. **Core hypothesis (the whole skill rests on this):** historical bug-triggering programs contain rare, valuable *code ingredients* — special values (`NaN`, `inf`, `INT_MAX`, empty/oversized inputs), edge-case shapes/sizes/lengths, 0-size dimensions, unconventional use of the target — that ordinary LLM generation never produces. LLMs trained on GitHub generate *typical* programs; fuzzing wants *unusual* ones. FuzzGPT closes that gap by priming the LLM with real past bugs instead of asking it to be "creative." This is the unusual-input engine. It pairs with `vuln-research` (which decides *what* to target and triages findings); FuzzGPT decides *how* to generate inputs that actually hit edge cases. ## The unit you fuzz: the "fuzz target" FuzzGPT steers generation toward one **fuzz target** at a time — the specific unit of functionality you want to stress (here, *the unit you point generation …
Read the whole file at its exact version.
How to install
mdr add lu1sdv/skillsmd/fuzzgpt@git:20260922.ae9c57dmdr add lu1sdv/skillsmd/fuzzgpt@sha256:59fc33643f597211Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_fp6vbrroigriuhjx)
1 badge views in 30 days
Versions
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (9125 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
lu1sdv/skillsmd · 2 stars · license none · pushed 2026-09-22 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_fp6vbrroigriuhjx GET https://markdownregistry.com/api/v1/resolve?ref=lu1sdv/skillsmd/fuzzgpt GET https://markdownregistry.com/api/v1/blob/59fc33643f5972113858c23ca279fd660308793d21c9ff0bf82c3d5a2fd2cd16
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.