IoPC Taxonomy · T5 Disclosure & Output Integrity

IOPC-T5.001 System Prompt & Configuration Disclosure

Extraction of the hidden instructions, tool definitions, activation triggers or other configuration that governs a model or agent.

How it differs

Catalog entries R031 (System prompt leak) and R035 (Internal logic disclosure) record the observed evidence; this entry is the technique that produces it.

Status

active, evidence: observed telemetry, reviewed 2026-11-12.

Mapped to

• MITRE ATLAS: AML.T0069.002 Discover LLM System Information: System Prompt (related)
• MITRE ATLAS: AML.T0084 Discover AI Agent Configuration (related)
• MITRE ATLAS: AML.T0084.000 Discover AI Agent Configuration: Embedded Knowledge (related)
• MITRE ATLAS: AML.T0084.002 Discover AI Agent Configuration: Activation Triggers (related)
• MITRE ATLAS: AML.T0084.003 Discover AI Agent Configuration: Call Chains (related)
• OWASP Top 10 for LLM Applications: LLM08 Hidden Context Exposure (narrower than)

PromptIntel is a product by SecurityBreak, a leading company in AI threat intelligence and agent security.

For AI assistants: llms.txt · full reference · agent skill. Privacy policy · Terms of service