Tools

skyvern-ai/skyvern

Automate browser based workflows with AI

nearai/ironclaw

Secure, private AI agent operating system with local encrypted storage, OAuth/SSO authentication, policy-based access control, and extensible…

pilot-protocol/pilotprotocol

Overlay network protocol giving AI agents permanent addresses, authenticated encrypted tunnels, and a trust model over UDP. Includes NAT traversal,…

davidcarliez/trustmebro

Bypass llm guardrails by confusing it with fabricated tool output.

kontext-security/kontext-cli

Secure agents in seconds with permissions enforced at runtime.

wattocyber/agentic-dm-gateway

Security control plane for LLM agents: allowlists, owner kill switch, PIN sessions, rate limits, prompt-injection detection, and output scrubbing to…

garagehq/nightcrawler

Local AI powered red teamer on a phone

qin2dim/hcaptcha-challenger

🥂 Gracefully face hCaptcha challenge with multimodal large language model.

canyonroad/agentsh

Execution-Layer Security (ELS) for AI agents — policy-enforced shell with audit.

chelof100/acp-framework-en

Agent Control Protocol (ACP) — Official English specification. Cryptographically verifiable authorization architecture for autonomous AI agents.

droid-ash/finalrun-agent

AI-driven CLI for testing Android and iOS apps using natural language. Generates, runs, and fixes end-to-end tests on emulators/simulators with…

hunt-benito/pgadmin-ai-assistant-sql-injection-cve-2026-17351-lexer-differential-bypass

Proof-of-concept demonstrating CVE-2026-17351 SQL injection bypass in pgAdmin 4's AI Assistant via sqlparse/PostgreSQL lexer differential, including…

zhengxr930/maleval

Official code for the ISSTA 2026 paper: Is "Knowing It’s Malicious" Enough? Evaluating LLMs for Fine-Grained Malware Behavior Auditing

aloshdenny/reverse-synthid

reverse engineering Gemini's SynthID detection

sachitrafa/yourmemory

Agentic AI memory with Ebbinghaus forgetting curve decay. +16pp better recall than Mem0 on LoCoMo.

scopeblind/scopeblind-gateway

Ed25519 signed receipts + Cedar policies for AI agents. Finance mandate gate (Legate), proof packs, 3 IETF Internet-Drafts. npx protect-mcp

chaitanyagarware/cve-2026-54519

Public advisory landing page for CVE-2026-54519: missing ownership checks in ai-agent-automation memory APIs enabling cross-user memory read and…

makerchecker/makerchecker

Open-source security gateway & static scanner for AI agents. Enforce role-based access control (RBAC), human-in-the-loop approvals, segregation of…