TAG: AI-SECURITY

200 AI agent skills, hardened with targeted behavioral guardrails. Free drop-in replacements.

Production-ready AI AppSec skills for SAST, threat modeling, remediation, PR security review, and serialization abuse analysis.

Security scanner for AI skill files (SKILL.md) and bundled code (scripts/, tools/). It helps you catch high-risk patterns before publishing or running a skill.

Antigravity. Claude-code. 🇬🇧 Zero-dependency Node.js CLI to statically audit third-party AI Skills for malicious code patterns before local execution. | 🇪🇸 CLI Node.js sin dependencias para auditar estáticamente Skills de IA buscando código malicioso antes de ejecutarlos.

AgenticStore: The secure toolkit for AI agents. Instantly equip Claude Desktop, Cursor, and Windsurf with 27+ MCP tools, persistent memory, and SearXNG search, all protected by a built-in PII prompt firewall to protect your data from being exposed to AI agents.

Security scanner for OpenClaw skills, MCP servers, and agent tools. Detects prompt injection · data exfiltration · supply chain attacks — in under 10 seconds.

Security scanner for detecting malicious AI skills and instruction files

Deterministic Java security remediation skills mapped to MITRE CWE vulnerabilities for AI coding agents and DevSecOps platforms.

GitHub Action: pin approved AI Skill behavior; block unapproved drift in CI.

Analyze code with AppSec skills for SAST, threat modeling, PR review, and serialization audits using evidence-first security workflows

# 🔐 Agent Security Eval A lightweight framework for **adversarial testing of AI agents** (Claude, OpenAI, custom agents). This project helps identify: * Prompt injection vulnerabilities * Tool misuse / unsafe execution * Data leakage risks * Weak agent behavior under adversarial inputs ---