agentleFS
Sign inStart free
MasriyanMasriyan/gemini-security-skills/skills/exploit-development/SKILL.md

exploit-development

Skill4 starsChanged 5 months agoMITView on GitHub

Authorized exploit development and vulnerability research skill for lab environments, CTFs, owned software, crash analysis, memory corruption, exploitability assessment, fuzzing results, proof-of-concept design, and remediation. Use for defensive validation and education; avoid real-world weaponization, stealth, persistence, evasion, or unauthorized targets.

We split this skill into the rules it gives an agent

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Keep proof of concept minimal: demonstrate the bug and impact without persistence, evasion, automated exploitation at scale, or …

    line 11
  2. Distinctive:

    Prefer root-cause analysis, exploitability classification, mitigations, and regression tests.

    line 12

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Exploit Development

Authorization Boundary

  • Work only on owned code, lab targets, CTFs, or explicitly authorized research.
  • Keep proof of concept minimal: demonstrate the bug and impact without persistence, evasion, automated exploitation at scale, or post-exploitation.
  • Prefer root-cause analysis, exploitability classification, mitigations, and regression tests.

Workflow

  1. Establish target version, build flags, architecture, mitigations, input vector, and crash artifact.
  2. Reproduce deterministically in an isolated lab with symbols and sanitizer output when possible.
  3. Triage root cause: bounds, lifetime, type confusion, race, injection, logic flaw, or unsafe parser behavior.
  4. Assess exploitability at a high level: control of instruction pointer, write primitive, info leak, sandbox, and mitigations.
  5. Provide a safe PoC or pseudocode only as needed to validate impact, then produce patch guidance and tests.

Defensive Outputs

  • Crash summary with environment and reproduction constraints.
  • Root-cause explanation tied to source or disassembly.
  • Severity rationale and affected versions.
  • Patch strategy, hardening recommendations, and regression/fuzz tests.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free