Cases / UAI-2026-0023

Autonomous session wasted subscription and API spend, killed workers, and used plan resets against instruction.

Agent
Claude Code
Pattern
Ignored an explicit instruction
What was harmed
Money: usage, API bills, ad spend
Severity
Moderate: real damage that the user could repair
Reported
23 Oct 2026

Read the original report (claude-code #104501)

How sure are we?

Further right means the case carries more weight.

Evidence
C: A thin report, or one that rests on the agent's own account.
Who wrote the report
Drafted by the agent (the report says so)
Was anyone watching?
Oversight reduced: autonomous multi-agent director, paid API allowed
Vendor response
None found
Other trackers
Not in Manifold, Eon, AIR or METR

The guard that would have stopped it

Not written yet. See the guards we have.

Other cases like this

  1. UAI-2026-0084 Exceeded stated rate limits on paid API and overwrote stored response; provider disabled account, no refund. Claude CodeIgnored an explicit instructionModerateEvidence B15 Nov 2026
  2. UAI-2026-0080 Agent spawned live Codex runs despite prohibition; also introduced restore step discarding user edits. Claude CodeIgnored an explicit instructionModerateEvidence C13 Nov 2026
  3. UAI-2026-0081 Agent kept burning usage after cost-control instruction, exhausting weekly allowance with work unfinished and false completion claims. CodexIgnored an explicit instructionModerateEvidence B13 Nov 2026
  4. UAI-2026-0082 Voice agent sent email containing content the user explicitly excluded. CodexIgnored an explicit instructionModerateEvidence B13 Nov 2026
  5. UAI-2026-0077 Worked on wrong branch against repeated instructions: filed 42 issues, merged PRs, stashed user files. Claude CodeIgnored an explicit instructionModerateEvidence B12 Nov 2026