Plugin Claude Code
CVE hunting harness for open source security research. A 5-agent team that systematically finds, validates, and reports real vulnerabilities in open source packages.
Plugin Claude Code
CVE hunting harness for open source security research. A 5-agent team that systematically finds, validates, and reports real vulnerabilities in open source packages.
Instructions file
Instructions for ByamB4/find-cve-agent, covering claude.md -- find-cve-agent, project overview, agent team architecture, communication rules and ethical guardrails.
Agent
PoC builder and exploit chainer. Takes Hunter findings and builds working proof-of-concept exploits. Always seeks to escalate impact through vulnerability chaining.
Agent
Code review specialist. Performs deep source code analysis to find security vulnerabilities by tracing data flows from untrusted input sources to dangerous sinks.
Agent
Target discovery agent. Finds promising open source packages for security review by analyzing npm/PyPI/GitHub registries, download counts, and attack surfaces.
Agent
Research tracking agent. Maintains REGISTRY.md as the single source of truth. Prevents duplicate work, records all outcomes, and answers status queries from other agents.
Agent
False positive elimination specialist. Runs 6-gate verification process on every finding. Only CONFIRMED findings proceed to submission. Fail 3x = FALSE POSITIVE, no exceptions.
Command
Query NVD and OSV.dev for existing CVEs. Usage: /check-nvd . Shows CVE count, severity breakdown, and recent fixes.
Command
Take a confirmed vulnerability pattern and find the same bug in similar packages. Usage: /cross-pollinate (run after confirming a finding).
Command
Run the 6-gate false positive elimination process on the current finding. Usage: /fp-check (run from a target directory with findings).
Command
Full CVE hunting pipeline. Usage: /hunt . Orchestrates all agents: registry check, clone, code review, PoC build, validation, and report generation.
Command
Find targets in a category. Usage: /recon . Examples: /recon csv-parsers, /recon template-engines, /recon archive-libs.
Command
Query or update the research registry. Usage: /registry [query]. Examples: /registry stats, /registry check lodash, /registry list in-progress.
Command
Generate a disclosure report from the current finding. Auto-detects the best submission channel. Usage: /report (run from target directory with confirmed finding).
Skill Claude CodeCodex
Mine GitHub Security Advisories and CVE databases for incomplete fixes, finding variant vulnerabilities in patched code or similar patterns in related packages.
Skill Claude CodeCodex
Detect authentication and authorization bypass vulnerabilities including missing auth middleware, JWT algorithm confusion, IDOR, and session fixation.
Skill Claude CodeCodex
Detect code injection vulnerabilities in packages that dynamically generate or evaluate code via new Function(), eval(), vm.run, or template literal interpolation.
Skill Claude CodeCodex
Detect OS command injection via shell execution sinks where user-controlled input reaches system commands without proper sanitization.
Skill Claude CodeCodex
Cross-pollination multiplier technique: find a vulnerability in one package, then search for the same pattern across all similar packages to multiply findings.
Skill Claude CodeCodex
Detect decompression bomb vulnerabilities where compressed input can expand to exhaust memory, targeting buffer-based decompression without size limits.
Skill Claude CodeCodex
Detect XML/SVG/YAML entity expansion (Billion Laughs) vulnerabilities in parsers that allow unbounded entity definitions.
Skill Claude CodeCodex
Systematic false positive elimination for security findings. 6-gate verification, 13-item checklist, devil's advocate questioning. MANDATORY before any CVE submission.
Skill Claude CodeCodex
Detect JWT implementation vulnerabilities including algorithm confusion, none algorithm acceptance, weak secrets, and JWK injection attacks.
Skill Claude CodeCodex
Detect method clobbering via user-controlled object keys that overwrite built-in methods like toString, valueOf, or hasOwnProperty, causing crashes or logic bypass.