Controls › C-D2
Halt and hand off on uncertainty or refusal
The minimal-risk condition: when blocked or unsure, stop and ask.
Decision layerMissing or failed in 1 case (1 ended in harm)Worked in 0Machines: 1
Where it was missing or failed
The third column is what this control would have looked like in that case: the concrete form, not the abstract name.
| Case | World | What it would have looked like here | Status | Outcome |
|---|---|---|---|---|
| Benavides v. Tesla 2025 | Machines | Stop at end-of-road | absent | Ended in harm |
Recent signals touching this control
| Date | Signal | Kind |
|---|---|---|
| 2026-10-20 | CVE-2026-109444: OpenSRE The National Vulnerability Database (NVD) record says instructions injected into alerts or Slack messages triaged by the OpenSRE agent (through 0.1.2026.10.19) can make it run shell commands without confirmation, because the approval check in headless mode always allows execution. Source ↗ | vulnerability |
| 2026-10-16 | CVE-2026-77474: destructive_command_guard (dcg) The National Vulnerability Database (NVD) records that before 0.6.6 destructive_command_guard, a command-line safety tool that blocks destructive shell commands before AI coding agents run them, can be driven into exponential-time rescanning by nested or unclosed $( or $(( sequences, and the hung PreToolUse hook fails open so the destructive command proceeds; fixed in 0.6.6. Source ↗ | vulnerability |
Deploying something? Check a deployment ranks every control against the cases that match your profile. Patterns shows where this control fails across worlds.