vulnerability-research SKILL.md skillA
vulnerability-research from iuliandita/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add iuliandita/skills/vulnerability-research@git:20261105.aa96fb6Pins git:20261105.aa96fb6 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- iuliandita/skills
- Path
skills/vulnerability-research/SKILL.md- Versions recorded
- 7
- Latest version
- git:20261105.aa96fb6, committed Nov 5, 2026
- First version recorded
- Sep 20, 2026
- Size
- 27,479 bytes
- Repository stars
- 11
- License
- MIT
Find undisclosed vulnerabilities in authorized targets: code analysis, reverse engineering, patch diffing, fuzzing, PoC, disclosure report. Use for bug bounty.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Vulnerability Research and Discovery Systematic methodology for finding novel, undisclosed vulnerabilities in source code, compiled binaries, and live systems. This skill guides the research process from intelligence gathering through proof-of-concept development to responsible disclosure. This is the *discovery* skill - it finds vulnerabilities nobody has catalogued yet. For exploiting known weaknesses on live systems, use **privilege-escalation** (opt-in; if installed). For scanning code against known vulnerability patterns, use **security-audit**. **Target versions**: see `references/versions.md` (verified per the receipt date in that file). Do not restate version numbers here. ## When to use - Hunting for undisclosed vulnerabilities in a codebase, binary, or running service - Variant analysis after a CVE is published (finding similar bugs in related code) - Patch diffing - analyzing what a security update fixed to find nearby issues - Developing proof-of-concept exploits for discovered vulnerabilities - Attack surface mapping before a focused security engagement - Gathering threat intelligence on a target's technology stack - Preparing responsible disclosure reports …
Read the whole file at its exact version.
How to install
mdr add iuliandita/skills/vulnerability-research@sha256:0d0559384d9874dbThe line at the top of this page pins the label git:20261105.aa96fb6, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_yn42ycswc6xh3ras)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 7 versions of this file, between Sep 20, 2026 and Nov 5, 2026, about one every 8 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261105.aa96fb6 latest | 2026-11-05 | aa96fb6 | 27,479 B | A | view · diff |
| git:20261105.305fe01 | 2026-11-05 | 305fe01 | 27,601 B | A | view · diff |
| git:20261105.65c9c02 | 2026-11-05 | 65c9c02 | 27,603 B | A | view · diff |
| git:20261028.640b16a | 2026-10-28 | 640b16a | 27,290 B | A | view · diff |
| git:20261002.a7f9a1c | 2026-10-02 | a7f9a1c | 27,303 B | A | view · diff |
| git:20260920.ebf9a3d | 2026-09-20 | ebf9a3d | 27,550 B | A | view · diff |
| git:20260920.ac01853 | 2026-09-20 | ac01853 | 27,411 B | A | view |
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 (27479 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
iuliandita/skills · 11 stars · license MIT · pushed 2026-11-05 · branch develop
API
GET https://markdownregistry.com/api/v1/artifacts/art_yn42ycswc6xh3ras GET https://markdownregistry.com/api/v1/resolve?ref=iuliandita/skills/vulnerability-research GET https://markdownregistry.com/api/v1/blob/0d0559384d9874dbf1c6087e170456863a9aba008db72b2a6869e85c1bef12b6
Your AI assistant 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.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.