IoPC Taxonomy · T1 Instruction & Input Injection

IOPC-T1.001 Direct Prompt Injection

Attacker-authored instructions supplied directly in the user-controlled input channel to override system or developer intent.

How it differs

Canonical form of registry entry IOPC-R001. Distinguished from Indirect Prompt Injection by the ingress surface: the attacker is the direct input author.

Status

active, evidence: mixed, reviewed 2026-11-12.

Mapped to

• CSA Autonomous Action Runtime Management (AARM): T1 Prompt Injection (related)
• Google Secure AI Framework (SAIF): control:Input Validation and Sanitization Input Validation and Sanitization (control relevant)
• Google Secure AI Framework (SAIF): risk:Prompt Injection Prompt Injection (narrower than)
• MITRE ATLAS: AML.T0051 LLM Prompt Injection (narrower than)
• MITRE ATLAS: AML.T0051.000 LLM Prompt Injection: Direct (equivalent)
• OWASP Top 10 for Agentic Applications: ASI01 Agent Goal Hijack (related)
• OWASP Top 10 for LLM Applications: LLM01 Prompt Injection (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