Zp Cve — Security skill for Claude Code
Known-CVE check - version fingerprint to confirmed finding, backed by KEV and the local exploit corpora.
How to install Zp Cve
Installs to ~/.claude/skills/maramharsha-zeroprotocol-zp-cve/SKILL.md
mkdir -p ~/.claude/skills/maramharsha-zeroprotocol-zp-cve && curl -fsSL https://raw.githubusercontent.com/MaramHarsha/ZeroProtocol/HEAD/commands/zp-cve.md -o ~/.claude/skills/maramharsha-zeroprotocol-zp-cve/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Zp Cve does
name: zp-cve description: "Known-CVE check - version fingerprint to confirmed finding, backed by KEV and the local exploit corpora. Usage: /zp-cve CVE-2021-44228 | /zp-cve host.target.com"
/zp-cve
Load `skills/zp-cve/SKILL.md`. Target: **$ARGUMENTS**
zp-reports cve CVE-YYYY-NNNNN # KEV status + nuclei template + PoCs + Exploit-DB
zp-reports status # what corpora are synced
zp-reports sync all # ~2.5 GB, local only
Prioritise by CISA KEV fi
Alternatives in Security
- Exploit 2.3k ★
- Cve MCP Server — Production-grade MCP server giving Claude 27 security intelligence tools across 21 APIs — CVE lookup, EPSS sco 1.2k ★
- /chain — Build an A→B→C exploit chain for higher severity and payout 927 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
POC
Generate an executable proof-of-concept exploit for a confirmed High/Critical finding — detect the toolchain,
Scan Cves
Run a focused nuclei CVE sweep against a host or recon directory, optionally filtered by year. Runs log4j-scan
Characterize Agent
Step 1 of an agent pentest — fingerprint the target before sending any payload. Maps visibility, tool allowlis
Pentest
Run an AI-powered penetration test against a target URL + source code repo. Usage: /pentest [--config ] --ski
Cve Freshness Loop
Turn a fresh CVE disclosure into a running probe in minutes — KEV/EPSS feed → variant pack or ad-hoc probe → o
Hunt Agent
Start an agent pentest. Fingerprint the target agent, select applicable hunt-agent skills, run their probes, s
Related Agents
POC Engineer
Given a confirmed finding + its context worksheet, produces the smallest self-contained crate that reproduces
POC Builder
Build a minimal proof of concept for a confirmed security finding. Writes a failing test, a small script, or a
Finding Chain Synthesizer
Chains confirmed audit findings into multi-step, cross-domain exploit candidates and searches for a unique eme