47,133 repositories indexed
1–15 of 15 · Most stars
Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and supply-chain risks in Claude Code, Codex, and MCP skills before you install them.
Translateddsh-purge Community · Community-maintained edition of DeepSeek Harness: host compatibility, status diagnostics, prompt management, updates, and local backup and rollback. Based on dsh-purge by 小杨 (Xiao Yang) / YuJunZhiXue.
TranslatedOne-click replacement of the built-in prompts of three AI clients: DSH / WorkBuddy / ZCode. Double-click to use, self-verifiable, backup before changes, one-click restore. v8.29: card-style interface, activation code required to log in, automatic DSH plugin injection, official group verification. Single-file exe with no Python installation needed, completely free and open source.
Every practical and proposed defense against prompt injection.
Learn about a type of vulnerability that specifically targets machine learning models
TranslatedArmor-breaking (jailbreak) experiment project targeting GPT 6.0 and workbuddyV4.1flash
AI Agent Identity and Access Management and Inference Firewall
Open detection-rule standard for AI agent security threats — like Sigma, but for AI agents. Executable, testable rules for prompt injection, tool poisoning, context exfiltration and MCP attacks. Merged into open-source projects at Microsoft, Cisco, Gen Digital, MISP and FINOS. MIT-licensed.
Access control for AI agents. Set what Claude Code, Codex, Gemini, Cursor and any MCP server are allowed to do, review risky actions before they run, and keep every action on the record.
Runtime defense against memory poisoning in AI agents (OWASP ASI06). Drop-in for LangChain, OpenAI Agents, AutoGen, CrewAI and mem0.
A Hub/research area, for jailbreaking LLM's, and breaking their safety filters.
Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses | 500+ Papers | Perception, Cognition, Planning, Interaction, Agentic System
Open standard for Provenance & Intent Contracts (PIC) in AI agents. Verify intent, provenance, and evidence before high-impact tool calls.
Security training for the apps you actually ship. Open your browser and start hacking.
Prompt-injection firewall for LLM applications — 33 input detectors, 9 output scanners, federated ed25519-signed threat-intel feed. Apache 2.0, 1040 tests, F1 96.0% with 0% false positives. Docker, GitHub Action, LangChain/LlamaIndex/CrewAI integrations.