Context Modifiers
Attack-vector-specific modifiers applied through capped diminishing contribution logic.
Domain purpose
Attack-vector-specific modifiers applied through capped diminishing contribution logic.
Fields, modifiers, profiles and tests
CM-01Model Poisoning
Apply base contribution 2.0 subject to effective cap 1.5 (per-factor cap).
CM-02RAG leakage
Apply base contribution 1.5 subject to effective cap 1.5.
CM-03Prompt Injection
Apply base contribution 1.5 subject to effective cap 1.5.
CM-04Agent Hijack
Apply base contribution 1.5 subject to effective cap 1.5.
CM-05Agentic
Apply base contribution 1.0 subject to effective cap 1.0.
CM-06Adversarial
Apply base contribution 0.5 subject to effective cap 0.5.
Implementation use
Determine applicability using the framework scope and system context. Implementation should be proportionate to risk and supported by evidence sufficient to validate the intended outcome.
Practitioner and validation guidance
Apply context modifiers transparently, within documented caps, and retain the factor-level calculation trace.
- Validate the applicable profile and all conditional requirements.
- Retain source evidence, analyst rationale and transformation history.
- Record uncertainty and do not infer regulatory, certification or legal outcomes.