Trending repositories: prompt-injection

3 of 3 repositories

• NVIDIA/SkillSpector

  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.

  AI summary: A security scanner that detects vulnerabilities and malicious patterns in AI agent skills before execution.

  14,305securityPythonApache-2.0agent-securityagent-skillsagentic-aiai-security

• ifixai-ai/iFixAi

  Independent Auditing of AI Agents. Run by human or the agent itself, to answer the most crucial question in the AI Agent Economy. Is the agent doing what is supposed to do? With iFixAi you can have this answer in less than 120 seconds.

  AI summary: A fast, independent auditing CLI to evaluate AI agent safety, alignment, and hallucinations.

  6,558securityPythonApache-2.0agent-evaluationaiai-alignmentai-evaluation

• uber/ADR

  ADR secures enterprise AI agents through observability, security benchmarking, and threat detection. Deployed at Uber.

  AI summary: An enterprise security system developed by Uber to monitor, detect, and mitigate risks from AI coding agents.

  1,257securityPythonApache-2.0agent-securityai-agentsai-securitybenchmark