Security / AI Agent Security
An interactive CTF-style challenge where users try to break or exfiltrate data from sandboxed AI agents running in Declaw’s isolated runtime.
The page clearly presents a real AI-powered security challenge with multiple agent scenarios, visible difficulty levels, and concrete attack goals. It explains the product context, shows that the sandbox uses runtime policies and isolated sessions, and gives enough detail for a useful directory listing.
The snapshot does not show technical docs, setup instructions, or how the arena maps to Declaw’s broader runtime product. It also doesn’t explain whether results are persisted, how challenges are scored, or whether the scenarios are meant purely for demos, training, or ongoing testing.
Last evaluated 59 days ago. Current rank #876. Down 6 spots in the rankings.
Open-source security scanner for AI agents, MCP servers, and agent skills. It auto-discovers installed agent components and checks them for prompt injection, tool poisoning, secrets, malware payloads, and related risks.
Self-hosted AI security testing platform for authorized pentesting and bug bounty workflows, with a local web UI, live agent telemetry, verified findings, and branded PDF reports.
GitHub Marketplace app from NeuraLegion that scans apps and APIs for vulnerabilities, proposes fixes, and validates remediations inside GitHub workflows.
Belay is an open-source, local-first security layer for AI coding agents. It blocks dangerous commands, secret leaks, prompt injection, and risky MCP tool calls, with human approval flows and support for multiple agents.
