mcp-tea
Fetch your dataset, ask questions, and get concise summaries in seconds. Analyze JSON structure to uncover fields, patterns, and anomalies without manual digging. Use natural language to get answers grounded in your data.
0Tools
1Findings
Mar 24, 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
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
100%2 rules
Injection via prompt templates and runtime tool output