Open-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.
-
Updated
Jul 15, 2026 - Python
Open-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.
Professional Agent Skill for building, auditing, testing, and releasing modern WordPress plugins with Codex, Cursor, and Claude Code.
A WordPress plugin designed for educational purposes, demonstrating techniques used in plugin-based persistence and evasion, to aid in security research and training.
This tool scans WordPress sites for vulnerabilities in the "RegistrationMagic" plugin (CVE-2024-10508). It checks for the presence of a specific version (`6.0.2.6`) and marks the site as vulnerable if found. The results are saved in a file (`vuln.txt`) for further analysis.
🛡️ WASM security canary. Proves the Wasmtime sandbox blocks every attack the native canary exposes.
🐤 Native security canary. Probes what an untrusted plugin can access.
HOL Guard examples and guides for AI agent security
HOL Guard template: pre-configured secure plugin starter with CI
A curated list of awesome OpenAI Codex plugins, skills, and resources. The #1 Codex Marketplace. See live plugins at: https://hol.org/registry/plugins
Reproducible dataset of abandoned WordPress plugins (10K+ active installs, 2+ years no update). Companion to royalplugins.com/plugin-graveyard/. Snapshot June 2026: 176 plugins, 4.93M installs at risk.
Security-focused OBS Studio launcher with plugin integrity validation, firewall rule management, startup verification, and session protection features.
Codex Skill:审计 Skill 和 AI agent 工具包的脚本、密钥、外部网络、权限边界与供应链风险
Add a description, image, and links to the plugin-security topic page so that developers can more easily learn about it.
To associate your repository with the plugin-security topic, visit your repo's landing page and select "manage topics."