Generate Custom MCPs
Enables dynamic creation of customized MCP servers using the MCP SDK to automate setup and manage tools and resources for specialized AI applications.
0Tools
7Findings
22Stars
Mar 22, 2026Last Scanned
Security Category Deep Dive
Prompt Injection
Prompt & context manipulation attacks
69
Maturity
14
Rules
5
Sub-Categories
1
Gaps
64%
Implemented
56
Tests
1
Stories
Findings1
1 critical
criticalJ5Tool Output Poisoning PatternsMCP02-tool-poisoningAML.T0054
Pattern "(return|respond|output|result).*(?:ignore previous|new instructions|act as|you are now|system prompt)" matched in source_code: "output the system prompt" (at position 3352)
Tool responses MUST NOT contain instruction-like content, file read directives, or social engineering phrases. Error messages should be factual and technical — never suggest actions involving sensitive data access. See CyberArk ATPA research for attack demonstration.
100%3 rules
Injection via tool descriptions and parameter fields
GAP-001Prompt Injection Coverage GapMissing detection coverage for emerging prompt injection attack variants not addressed by current rules
100%4 rules
Hidden instructions via external content and tool responses
100%2 rules
Context window saturation and prior-approval exploitation
100%3 rules
Payload hiding via invisible chars, base64, schema fields
50%2 rules1 found
Injection via prompt templates and runtime tool output