Security / AI Security
A research writeup from AgentSploit analyzing 1,384 tools across 28 MCP servers, highlighting how tool descriptions, source tools, and sink tools create an attack surface for agents.
The page clearly describes an AI/security-related project with a concrete purpose, reproducible harness, and specific findings drawn from a large survey of MCP servers. It is useful for AI builders and security practitioners working with agents and MCP tooling.
This snapshot is a single markdown research page; it does not show the broader project navigation, package docs, or a complete product overview. A visitor cannot tell from this page alone how mature the framework is, what outputs the tooling produces, or how to use the survey workflow beyond the listed commands.
Last evaluated 16 days ago. Current rank #2473. Down 1 spot 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.
An AI harness for long-running penetration tests, bug bounties, and code audits. It combines specialist agents, a Kali runtime, durable state, and second-agent verification for findings.
Open-source security agent framework for cloud, code, and runtime. It ships 45 built-in agents for AWS, GCP, Azure, Kubernetes, GitHub, and GitLab, and lets users create custom agents in a single markdown file.
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.
