Dual control on irreversible actions
Wires, filings, ACL changes, and outbound mail require a second channel.
$6.7M experimental capital · 2 sources
Risk this mitigates
20Given that untrusted text is concatenated into model context in courts, enterprises, and consumer products, and prompt injection remains the leading unfixed LLM failure, there is a possibility of an adversary steering a model that drafts, ranks, or decides inside an institution resulting in corrupted legal filings, leaked data, and decisions that look official but were written by an attacker.
Residual composite 20 · still above the threshold
Effect if implemented
Applied to every failure scenario on that risk, then re-ranked. Axes are clamped at 1.
- Likelihood
- −0
- Consequence
- −2
- Urgency
- −0