POC — Security skill for Claude Code
Generate an executable proof-of-concept exploit for a confirmed High/Critical finding — detect the toolchain, pick the harness framework by finding type, spawn poc-engineer, and emit a one-command run.
How to install POC
Installs to ~/.claude/skills/solanabr-auditor-skill-poc/SKILL.md
mkdir -p ~/.claude/skills/solanabr-auditor-skill-poc && curl -fsSL https://raw.githubusercontent.com/solanabr/auditor-skill/HEAD/commands/poc.md -o ~/.claude/skills/solanabr-auditor-skill-poc/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What POC does
name: auditor:poc description: Generate an executable proof-of-concept exploit for a confirmed High/Critical finding — detect the toolchain, pick the harness framework by finding type, spawn poc-engineer, and emit a one-command runnable crate plus the earned [PoC-*] evidence tier. Never hard-fails: on toolchain absence it downgrades to [PoC-ATTEMPTED] and keeps the existing prose PoC. argument-hint: " [--fork] [--fuzz] [--force]" allowed-tools: Read, Grep, Glob, Bash,
Alternatives in Security
- Security Scan Report — Generated: 2026-04-10 20:48 UTC Skills scanned: 134 Total findings: 836 Critical: 32 High: 50 Safe skills: 100 18.1k ★
- Query Token Audit — Audit token security to detect scams, honeypots, and malicious contracts across BSC, Base, Solana, and Ethereu 483 ★
- Data Viz Audit — Audit a data visualization for chart type selection, accessible color palette, annotations, and anti-patterns 309 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Vuln Report Skill
Claude Code skill: turn confirmed vulnerabilities into submission-ready DOCX reports 漏洞报告成稿 skill(SRC/0day 提交稿
A11y Audit
Comprehensive accessibility audit — automated axe scan, keyboard navigation check, color contrast review, ARIA
Party
Spawn a pre-configured team of agents for a specific task type. Usage: /party . Available parties: archon-coun
Review Observability
Audit logging, metrics, tracing, and correlation IDs across pipelines and background jobs. Flags blackbox code
Skills Suggest
Audit recent sessions for repeated tasks and AI-output-then-manual-verification patterns. Produces a ranked li
Raze
MCP-first security orchestrator for Solidity smart contracts. Validates AI attack hypotheses, generates Foundr
Related Agents
POC Builder
Build a minimal proof of concept for a confirmed security finding. Writes a failing test, a small script, or a
POC Engineer
Given a confirmed finding + its context worksheet, produces the smallest self-contained crate that reproduces
Prototyper
The Prototyper builds rapid proof-of-concept implementations, throwaway spikes, and time-boxed experiments to