Invariant Labs
A company focused on security research for AI systems, known for naming and analyzing attack techniques targeting AI agents, including MCP tool poisoning and related threats in agentic AI deployments.
Timeline (last 90 days)
Invariant Labs在2025年4月1日首次将描述中夹带客户端界面不可见指令的现象命名为'工具投毒'（tool poisoning）。
Invariant Labs demonstrated an attack against the official GitHub MCP server: after planting a malicious issue in a public repository, the agent pulled data from the repository owner's private repositories and published it to a public pull request.
Invariant Labs pointed out that there is no bug in the GitHub MCP server code itself — it is the combination of capabilities that constitutes the vulnerability.
Invariant Labs coined the term for MCP tool poisoning attacks in April 2025.
All Facts (4)
Invariant Labs在2025年4月1日首次将描述中夹带客户端界面不可见指令的现象命名为'工具投毒'（tool poisoning）。
50%UnverifiedInvariant Labs pointed out that there is no bug in the GitHub MCP server code itself — it is the combination of capabilities that constitutes the vulnerability.
50%UnverifiedInvariant Labs demonstrated an attack against the official GitHub MCP server: after planting a malicious issue in a public repository, the agent pulled data from the repository owner's private repositories and published it to a public pull request.
50%UnverifiedInvariant Labs coined the term for MCP tool poisoning attacks in April 2025.
50%