IoPC Taxonomy · T9 Persistence, Propagation & Evasion
IOPC-T9.001 Agent Configuration & Prompt Logic Tampering
Persistent modification of what governs the agent — system prompt assembly, tool registry, agent configuration files or deployment settings — so the compromise survives the session without a new injection.
How it differs
Distinguished from Persistent Memory Poisoning (T2.002), which corrupts remembered content: here the executable configuration itself is rewritten.
Status
active, evidence: observed telemetry, reviewed 2026-11-12.
Mapped to
- Google Secure AI Framework (SAIF): risk:Model Deployment Tampering Model Deployment Tampering (related)
- MITRE ATLAS: AML.T0018.003 Manipulate AI Model: Modify Prompt Construction Logic (related)
- MITRE ATLAS: AML.T0081 Modify AI Agent Configuration (equivalent)
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