Incorrect Verification Rubber-Stamp

Properties

family: bypass
severity: systemic
triggerError: A verifier agent runs but applies shallow or misaligned checks, approving an artifact that contains a latent error.
mechanism: The verifier performs only low-level correctness checks (compilation, surface syntax) rather than high-level objective validation, so a flawed artifact clears review and its laundered "approved" status downstream signals to subsequent agents that further checking is unnecessary.
blastRadius: All agents and pipeline stages that consume the reviewed artifact treat it as trusted; the false-positive certification suppresses re-inspection across the whole downstream chain.
mast: [Cat 3]
detection: A held-out adversarial test suite (e.g., isomorphic perturbation, execution against held-out cases) that the verifier never saw; cross-checking the artifact against the high-level objective rather than only low-level proxies.
mitigation: Multi-level verification: pair a low-level checker with an independent high-level objective validator; require verifiers to justify approval against the task specification, not only surface properties.
source: Why Do Multi-Agent LLM Systems Fail? MAST taxonomy FM-3.3 (arXiv:2503.13657)

family: bypass
severity: systemic
triggerError: A verifier agent runs but applies shallow or misaligned checks, approving an artifact that contains a latent error.
mechanism: The verifier performs only low-level correctness checks (compilation, surface syntax) rather than high-level objective validation, so a flawed artifact clears review and its laundered "approved" status downstream signals to subsequent agents that further checking is unnecessary.
blastRadius: All agents and pipeline stages that consume the reviewed artifact treat it as trusted; the false-positive certification suppresses re-inspection across the whole downstream chain.
mast: [Cat 3]
detection: A held-out adversarial test suite (e.g., isomorphic perturbation, execution against held-out cases) that the verifier never saw; cross-checking the artifact against the high-level objective rather than only low-level proxies.
mitigation: Multi-level verification: pair a low-level checker with an independent high-level objective validator; require verifiers to justify approval against the task specification, not only surface properties.
source: Why Do Multi-Agent LLM Systems Fail? MAST taxonomy FM-3.3 (arXiv:2503.13657)