The COMPEL Glossary Graph visualizes relationships between framework terminology, showing how concepts interconnect across domains, stages, and pillars. Term nodes cluster by pillar affiliation while cross-references reveal semantic dependencies — for example, how risk appetite connects to control effectiveness, model governance, and assurance requirements. This network representation helps practitioners navigate the framework vocabulary and understand that COMPEL terminology forms a coherent conceptual system rather than isolated definitions.
COMPEL Glossary / GL-59
Prompt Injection Resistance
The measured ability of an AI system to reject or neutralize adversarial instructions injected via user input, retrieved documents, tool output, or other untrusted content channels.
What this means in practice
Scored against a fixed evaluation set covering direct injection, indirect injection via retrieved content, and tool-output poisoning. Results are reported per channel so that the weakest surface is visible to security owners.
Context in the COMPEL framework
A core Security metric. Evaluated by adversarial testing during Produce and monitored in Evaluate; feeds incident response playbooks in Learn.
Where you see this
Prompt Injection Resistance is most commonly referenced when teams work across the Produce , Evaluate and Learn stages — especially within the Agent Governance layer . It appears in governance artifacts, assessment instruments, and delivery playbooks wherever COMPEL is operationalized.
Related COMPEL stages
Related domains
Synonyms
injection resistance , prompt-injection score , indirect injection defense
See also
- Trust & Performance Dimensions — The eight continuous-measurement axes against which every AI transformation is evaluated in COMPEL: Value, Reliability, Safety, Responsibility, Compliance, Security, Sustainability, and Adoption.
- Jailbreak Resistance — A composite score of an AI system's ability to reject adversarial prompts designed to bypass its safety policies, measured against a fixed, versioned red-team test suite.
- Governance Control — A defined mechanism — preventive, detective, or corrective — that enforces policy compliance, mitigates identified risks, or ensures operational integrity for AI systems.