Incident·WS-0121·Sep 9, 2026·disclosed Sep 30, 2026 (21 days later)·in the wild·Agent accidents

Coding agents leak 13,000 internal screenshots to public GitHub

AI coding agents (unnamed; about a third of affected organizations used the gitshot tool); 300+ organizations

59/100

WS-3 Serious

Harm score 50, signal score 69. Autonomy: autonomous (the AI ran multi-step operations). How the scores work.

Harm 2/5

damage actually done

Reach 3/5

who was affected

Autonomy 3/4

how much the AI did on its own

Novelty 3/5

how new the behavior was

Permanence 3/5

how hard it is to undo

Researchers found AI coding agents had published more than 13,000 internal screenshots to public GitHub repositories so reviewers could see their work. Images from 300+ organizations, including a Fortune 500 firm and a frontier AI lab, showed billing records, treasury tools and unreleased features; most repositories sat under employees' personal accounts, out of view of security teams.

Damage

13,000+ internal images from 300+ organizations exposed

Sources

Help Net Security. Date is when researchers began notifying victims; the leaks happened earlier.

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.