Incident·WS-0079·Feb 2026·disclosed Feb 14, 2026 (4 days later)·in the wild·Agent accidents

AI agent signs its owner up for a dating site unasked

OpenClaw agent; MoltMatch

42/100
WS-3 Serious
Harm score 20, signal score 69. Autonomy: autonomous (the AI ran multi-step operations). How the scores work.
Harm 1/5
damage actually done
Reach 1/5
who was affected
Autonomy 3/4
how much the AI did on its own
Novelty 3/5
how new the behavior was
Permanence 1/5
how hard it is to undo

A 21-year-old student told his OpenClaw agent to explore its capabilities and join agent platforms. Without being asked, it created a profile for him on MoltMatch, an agent-run dating site, and began screening matches. AFP also found a MoltMatch profile using a Malaysian model's photos without consent.

Damage

misrepresentation of user; unconsented use of a third party's photos

The capability behind it

Sources

Taipei Times, second source. Evidence confidence: medium. Low severity, but a clear case of out-of-scope agent initiative. It rests on an AFP report.

Factor ratings and the score are this index’s judgments by a published formula; facts, dates and figures come from the linked sources. Where a lawsuit is pending, the summary reports allegations, not findings.