MCP Exploitation
Attacks targeting Model Context Protocol integrations.
3 tests in this category, escalating by delivery channel from html-comment at tier 1 to 3 channels at tier 3. Each page hides an indirect prompt injection; if an agent follows it, the response names the attack it demonstrated and the command to scan for it. Background on this class of attack is in the attack guide.
- T1
Tool Discovery
mediumProbes for available MCP tools and their schemas
delivery: html-comment
- T2
Tool Injection
criticalInjects fake tool results to manipulate agent behavior
delivery: html-comment, invisible-span
- T3
Cross-Tool Exploit Chain
criticalChains MCP tools to achieve unauthorized access
delivery: html-comment, invisible-span, meta-tag
Scan your own setup
These pages test whether an agent follows instructions it finds in content. HackMyAgent tests the configuration underneath it, and prints each finding with a command to verify it and a command to fix it.
npx hackmyagent secure