security-audit-skill
A coding-agent skill for multi-phase security audits with independently verified, machine-readable findings
하고 싶은 일이나 쓰는 앱으로 검색한 다음, 카테고리로 걸러 보세요.
Skill은 AI가 읽고 그 방식대로 일하게 하는 지시와 파일 묶음이에요. MCP server가 아니고 설치 방법도 달라요.
A coding-agent skill for multi-phase security audits with independently verified, machine-readable findings
Deepsec is a security harness for finding vulnerabilities in your codebase powered by coding agents
Terminal security for developers and AI agents. Intercepts homograph URLs, pipe-to-shell, ANSI injection, obfuscated payloads, data exfiltration, and malicious AI skills/configs before they execute.
gpt6 Astra-claude-grok4.7-deepseekv4.1flash-glm5.3-gemini破甲越狱 · 冷咖啡 BREAK//OPEN 工作台
검색어가 이름, 설명, 카테고리에 몇 개나 나오는지로 정렬하고, 그다음 스타 순이에요.
카드 보는 법:↓ 주간 다운로드i★ GitHub 스타i세 기둥: 리뷰 · 점검 · 사용 정도i업데이트 = 최신 버전을 레지스트리에 공개한 날i
Causal Proof Engine for AI agents: signed log, zero vectors, failures traced to their cause.
Protect your AI agents and IDEs from malicious open-source packages.
Access control for AI agents and MCP servers: allow, hold for approval, or block each tool call
Exact-action approval for consequential agent actions: request, track, and verify signed receipts.
Evidence-backed AppSec for AI applications and agents. Powered by HAIEC.
AI supply-chain BOM: agents, MCP servers, packages and recorded reach. Scan and investigate via MCP.
A policy enforcement plane for MCP: pins every tool, holds risky calls, enforces egress policy.
Authorize consequential AI agent actions before execution
Give two agents on two machines the same encrypted folder. P2P, no cloud, only read bytes move.
Discover and call remote MCP tools as your own authenticated Agent Mesh member.
MCP server bridging Claude.ai/Desktop with self-hosted OpenClaw via OAuth 2.1.
MCP server exposing Signet cryptographic signing, verification, and content hash tools over stdio.
SecurityTrails MCP — wraps SecurityTrails API (securitytrails.com)
Read-only evidence for the tools agents run: MCP server records, coverage and policy.
Answer CTRLRun approvals from an MCP client: list what is held, inspect it, grant or deny.
Check tokens, pages and x402 payments before your agent trusts them. Offline verdicts.
Zero-secret MCP gateway for AI agents: risk-scored, audited calls with human-in-the-loop approval.
Check if an MCP server's tool definitions changed after approval, from a signed public log.
Community-built, comprehensive MCP server for the SecurityScorecard API (unofficial).
Formally-verified injection/exfiltration detector for AI agents (MCP-02).
Pre-tool policy enforcement + JSONL audit for AI agents. Apache 2.0.