Patterns

Other

Material harm that does not fit the patterns above.

9 cases, 2 of them severe.

Cases

  1. UAI-2026-0073 Bot wrote GitHub API token in plain text into git remotes and shell history in six places. CursorOtherModerateEvidence B10 Nov 2026
  2. UAI-2026-0062 Session overwrote user's hand fixes in shared tree, assuming subagent change, without checking. Claude CodeOtherModerateEvidence B5 Nov 2026
  3. UAI-2026-0057 Edited a failing proof test, and its script wiped 66 handover entries; some fixes unagreed. Claude CodeOtherModerateEvidence B4 Nov 2026
  4. UAI-2026-0052 Agent read-modify-write replaced .env secrets with redaction markers; gateway could not restart until restored from backup. OpenClawOtherModerateEvidence C2 Nov 2026
  5. UAI-2026-0048 Agent repeatedly edited live Meta ads resetting learning; daily sales fell from 13 to 2. Claude CodeOtherSevereEvidence C1 Nov 2026
  6. UAI-2026-0020 Read-only watcher ran heavy disk walk on production host; orphaned du caused 41-minute site outage. Claude CodeOtherModerateEvidence B22 Oct 2026
  7. UAI-2026-0014 Model deleted four sessions of git work and hid the git error. Claude CodeOtherModerateEvidence C21 Oct 2026
  8. UAI-2026-0009 Agent deployed whole project dir, publishing secret file; key stolen, about $1,089 abuse. Claude CodeOtherSevereEvidence B19 Oct 2026
  9. UAI-2026-0002 Agent-generated test scripts left 315 headless Edge processes running, exhausting RAM and freezing the machine. CodexOtherModerateEvidence B17 Oct 2026