#agent-security

🔁 Build reliable recurring AI-agent systems: 968 resources, 22 operational patterns, 22 loop contracts, 8 runtime starters, an interactive atlas, and a structured dataset.

Agent permission firewall for MCP tools, shell, files, and x402/Base payments.

DSH plugin security and dependency monitoring for DeepSeek Harness: exact vulnerable paths, breaking updates, and Agent follow-up.

Find where agent-controlled intent reaches consequential actions without an authority check. Python + TypeScript + Go. Zero-dependency SAST for AI agents.

An audit gate for AI agent outbound messaging: hold the draft, let a senior agent review it (no private-data leak, prompt-injection resistance), then release. Reference implementation.

Attack taxonomy, toolkit & defenses for persistent-memory poisoning of LLM agents. Author: Krishita Sanjay Choksi.

The authorization layer for AI agents — allow/deny/ask policy, human approvals, and tamper-evident receipts on every tool call. Zero-dep, framework-neutral, no SaaS.

AI Guardian Firewall — a local, user-space, agent-agnostic firewall that mediates an autonomous AI agent's actions (files, shell, network, services) with a deterministic policy boundary, a tamper-evident audit log, and a human-in-the-loop approval cockpit. No kernel modules. Apache-2.0.

Claude Code scaffold for building AI platforms securely — agent/LLM security, Kubernetes, SRE, observability, identity, and supply chain, grounded in published framework canon (OWASP, NIST, CIS, SLSA). Data-science lanes included.

Multi-agent collaboration trust measurement & red-team verification (R0, F1, cost, L0-L3). Offline-reproducible Mock baseline for GOAI 2026 Agent Infra.

Curated research on AI agent social engineering, manipulated delegation, prompt injection, tool-use boundaries, and agent security evaluation.

Source-backed archive of agent prompt-injection incidents, research records, trust-boundary patterns, schemas, and sanitized defensive summaries.

Runtime governance for AI agent tool calls: gates shell, filesystem, network, and credential access before execution.

A policy hook for Claude Code

Deterministic postcondition verification for AI agents and autonomous systems using independent observed state.

An auditable, bounded mediation layer for Claude in Chrome browser actions — content-blind action gating, with its own failure map published.

Unified open-source security shield for agentic AI systems — defense-in-depth prompt-injection protection (canary tokens, agent-trace alignment audit, tool-call guarding, PII/secret scanning).

Benchmarking schema-valid false tool observations and defense baselines for tool-using LLM agents.

Open-source trust layer for autonomous AI — gate agent, robot, smart home, and industrial actions before they run. Policies, HITL, Ollama/OpenAI, audit. MIT. npm @sanctum-runtime/sdk