Search
LayerFault
AI model: LayerFault/agent-mcp-overbroad-scopes
DecoyShield contributors
Web-layer counter-recon honeypot against agentic LLM attackers — drops invisible-to-human, visible-to-LLM payloads into your Flask/HTTP responses to halt, stall, or fingerprint AI-driven penetration scans.
...moreNicholas-Kloster
Agentic LLM injection benchmark — VisorCorpus payload delivery, VisorSD target discovery, HIT/MISS matrix per vector
weidutech
Autonomous Penetration Testing Agent Framework with External State Memory & Anti-False-Falsification Guardrails.
zhaji2333
基于 pi 的渗透测试 / SRC 漏洞挖掘 Agent：确定性信息收集 + LLM 编排挖洞 + 漏洞复审 + Vue3 Web 指挥台
yashchauhan66
Soter is a safety layer for AI chatbots, agents, RAG systems, and LLM applications.
Mayur021
Blast radius modeling framework for agentic systems — 5 axes (action class, chain depth, external reach, reversibility window, identity scope), OSI cross-walk, and standards alignment.
...moreFish121380
Deterministic pre-execution safety gate for AI agents: verify tool calls against trusted evidence, policies, and WorldState before side effects.
...moresevten
Pi extension that masks sensitive data before it reaches the LLM and restores it for users and tools.
Automated documentation system for Kali Linux tools using an AI agent. Scans, indexes, and documents your system tools automatically.
...morerudrendu_paul_packages
Adapter shapes (per-tool governedTool and dispatcher-style governedExecutor) for wiring toolgovern into an open-multi-agent-style tool-executor call site.
...moreturtlepusher
Browser automation for AI agents - integrates agent-browser with cognition swarms
7anX
AI protocol scanner — discover exposed MCP servers, A2A Agent Cards, and open LLM APIs in one command. 一条命令盘点 MCP、A2A Agent Card 和 LLM 开放接口暴露面。
...moreLayerFault
AI model: LayerFault/precision-benign-mcp-examples
LayerFault
AI model: LayerFault/agent-mcp-contradictory-tool-annotation
Capability-based safety gates for LLM agents. The model proposes; signet authorizes.
GitHub Actions
Guardrails for coding agents, decided by TypeSafe's Jev: blocks destructive commands, catches prompt injection, pushes back on an unverified done and routes effort per turn. For Claude Code, pi and omp.
...morerocketlang
Memory poisoning detection primitives for AI agents — pure pattern matchers (RAG trust, agent-role imperatives, tool-output poisoning, capability expansion, injection fingerprints) + opt-in Agentic Control Center event bus. Extracted from chitta-guard.
...more