Advisory Mining (find-cve-agent)

Multi-agent CVE-hunting plugin with OSV/NVD lookups and false-positive gates

Works with setup

Test report

Verdict
Works with setup
Score
4.8/10
Tested
Jul 17, 2026
Environment
Claude Code 2.x (agent harness)
Upstream re-checked
Jul 30, 2026 · 6e0a14b

This skill is no longer available upstream. Our re-check on Aug 10, 2026 couldn't find it any more (repo unreachable/deleted). The test below is what we measured on Jul 17, 2026 and we're leaving it up as a record — but there is nothing left to install, so we've removed the command.

This is a Claude Code plugin, not a skill: there is no SKILL.md or skill frontmatter anywhere in the repo, so copying it into ~/.claude/skills produces no loadable, auto-triggering skill - it only works through its install.sh plugin path and explicit /hunt slash commands. The bundled scripts are real and ran live: check-osv.sh returned 16 genuine advisories for PyPI 'requests', but the actual find-a-new-CVE payoff needs a chosen target and can't be shown to beat a no-skill baseline here.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

  • Installs cleanly 2/5
  • Triggers reliably 2/5
  • Output vs. baseline 5/10
  • Docs & honesty 3/5

What Advisory Mining (find-cve-agent) does

A Claude Code plugin (not a SKILL.md skill) that provides a 5-agent workflow, language-specific grep patterns, a false-positive knowledge base, and shell scripts to query OSV.dev and NVD for hunting variant vulnerabilities in open-source packages. Installs via its install.sh into a project's .claude/ directory and is driven through slash commands like /hunt and /recon.

How to install Advisory Mining (find-cve-agent)

Nothing to install: the source repository no longer has this skill. If the author brings it back, our daily re-check will pick it up and the command will reappear here.

Commands — how to trigger Advisory Mining (find-cve-agent)

  • /advisory-mining Multi-agent CVE-hunting plugin with OSV/NVD lookups and false-positive gates

It also activates on plain-language prompts like these:

  • Check if this PyPI package has any known vulnerabilities
  • Hunt for variant CVEs similar to this one in our dependencies
  • Look up OSV advisories for the requests library

Frequently asked questions

Is the Advisory Mining (find-cve-agent) skill free?
Yes. The skill itself is free from ByamB4/find-cve-agent. SkillProof publishes the install command and an independent test verdict at no cost.
Does Advisory Mining (find-cve-agent) work with Claude Code?
We tested it with Claude Code 2.x (agent harness) on Jul 17, 2026. Verdict: Works with setup. This is a Claude Code plugin, not a skill: there is no SKILL.md or skill frontmatter anywhere in the repo, so copying it into ~/.claude/skills produces no loadable, auto-triggering skill - it only works through its install.sh plugin path and explicit /hunt slash commands. The bundled scripts are real and ran live: check-osv.sh returned 16 genuine advisories for PyPI 'requests', but the actual find-a-new-CVE payoff needs a chosen target and can't be shown to beat a no-skill baseline here.
What is the Advisory Mining (find-cve-agent) SkillProof Score?
4.8/10 — installs cleanly 2/5, triggers reliably 2/5, output vs. baseline 5/10, docs & honesty 3/5.
How do I install Advisory Mining (find-cve-agent)?
Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Advisory Mining (find-cve-agent) with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.