N/A
Omprakash97/Cursor Agent Poisoning
A proof-of-concept attack that exploits Model Context Protocol (MCP) tool registration to achieve persistent agent poisoning in AI assistants like Cursor, embedding malicious instructions that persist across chat contexts without requiring tool execution.
Scan Scheduled
This agent is queued for security scanning. It will be graded in the next scan batch.
What We Know
- URL https://glama.ai/mcp/servers/akwx1lhi2q
- Framework mcp
- Sources glama
- First Seen Mar 16, 2026
- Repository github.com/Omprakash97/exploit-mcp
Browse more:
Search all agents
Ecosystem Report