🛡️ A curated list of resources on agent skills security: attacks, defenses, frameworks, and benchmarks for securing AI agent tool use and skill ecosystems
GitHub repository with 17 stars and 15 forks.
Topics: agent-security, ai-safety, awesome-list, llm-security, mcp, owasp, prompt-injection, tool-use
Trending score 1.10, freshness score 0.80, stars gained +1, forks gained +0.
2026-06-15: 17 stars and 15 forks.
Sandbox any AI agent in seconds - zero setup, zero latency.
GitHub repository with 2,683 stars and 186 forks.
Trending score: 2.45; stars gained: +14; forks gained: +0.
Language: Rust
Topics: agent-sandbox, agent-security, ai-agent-sandbox, ai-agent-security, ai-agents, ai-security
A local control plane for AI agents — see what they do, approve what matters, keep secrets out. Rust + Tauri + Chrome MV3.
GitHub repository with 392 stars and 24 forks.
Trending score: 1.98; stars gained: +3; forks gained: +0.
Language: Rust
Topics: agent-security, ai-agents, audit-log, desktop, llm, local-first
Agent Beacon is the world's first open-source telemetry layer for AI agents wherever they run: locally, in CI, or in the cloud.
GitHub repository with 229 stars and 8 forks.
Trending score: 1.91; stars gained: +5; forks gained: +1.
Language: Go
Topics: agent-ai-cli, agent-security, ci, cloud, endpoint-security, mobile-device-management
Open-source AI agent firewall for MCP security and agent egress. Scans mediated HTTP, MCP, A2A, and WebSocket traffic for exfiltration, SSRF, and prompt injection, and emits mediator-signed action receipts: verifiable audit evidence from outside the agent.
GitHub repository with 718 stars and 82 forks.
Trending score: 1.79; stars gained: +6; forks gained: +0.
Language: Go
Topics: agent-security, ai-agent-security, ai-agents, ai-firewall, ai-security, dlp
Agentic LLM Vulnerability Scanner / AI red teaming kit 🧪
GitHub repository with 1,904 stars and 266 forks.
Trending score: 1.60; stars gained: +5; forks gained: +3.
Language: Python
Topics: agent-framework, agent-security, ai-red-team, llm-evaluation, llm-evaluation-framework, llm-fuzzer
Fail-closed execution firewall for AI agents: quarantine MCP tools, proxy OpenAI-compatible requests, emit signed receipts, and verify EvidencePacks offline.
GitHub repository with 33 stars and 2 forks.
Trending score: 1.18; stars gained: +1; forks gained: +0.
Language: Go
Topics: ai-agents, ai-security, developer-tools, llm-security, mcp, model-context-protocol
Sandbox any AI agent in seconds - zero setup, zero latency.
GitHub repository with 2,683 stars and 186 forks.
Trending score: 2.45; stars gained: +14; forks gained: +0.
Language: Rust
Topics: agent-sandbox, agent-security, ai-agent-sandbox, ai-agent-security, ai-agents, ai-security
A local control plane for AI agents — see what they do, approve what matters, keep secrets out. Rust + Tauri + Chrome MV3.
GitHub repository with 392 stars and 24 forks.
Trending score: 1.98; stars gained: +3; forks gained: +0.
Language: Rust
Topics: agent-security, ai-agents, audit-log, desktop, llm, local-first
Agent Beacon is the world's first open-source telemetry layer for AI agents wherever they run: locally, in CI, or in the cloud.
GitHub repository with 229 stars and 8 forks.
Trending score: 1.91; stars gained: +5; forks gained: +1.
Language: Go
Topics: agent-ai-cli, agent-security, ci, cloud, endpoint-security, mobile-device-management
Open-source AI agent firewall for MCP security and agent egress. Scans mediated HTTP, MCP, A2A, and WebSocket traffic for exfiltration, SSRF, and prompt injection, and emits mediator-signed action receipts: verifiable audit evidence from outside the agent.
GitHub repository with 718 stars and 82 forks.
Trending score: 1.79; stars gained: +6; forks gained: +0.
Language: Go
Topics: agent-security, ai-agent-security, ai-agents, ai-firewall, ai-security, dlp
Agentic LLM Vulnerability Scanner / AI red teaming kit 🧪
GitHub repository with 1,904 stars and 266 forks.
Trending score: 1.60; stars gained: +5; forks gained: +3.
Language: Python
Topics: agent-framework, agent-security, ai-red-team, llm-evaluation, llm-evaluation-framework, llm-fuzzer
Fail-closed execution firewall for AI agents: quarantine MCP tools, proxy OpenAI-compatible requests, emit signed receipts, and verify EvidencePacks offline.
GitHub repository with 33 stars and 2 forks.
Trending score: 1.18; stars gained: +1; forks gained: +0.
Language: Go
Topics: ai-agents, ai-security, developer-tools, llm-security, mcp, model-context-protocol