Level 3. Significant control incident
AI models keep posting screenshots showing sensitive data from inside tech companies
- Developer
- Not established
- Model
- Not established
- When it happened
- Not established
- When it was disclosed
- October 8, 2026
- How well it is stood up
- Not verified yet
- What caused it
- Not established
- Where it stands now
- Not established
What happened
Reported by thehackernews.com, dated 2026-10-08. Listed here with a link to their report. Nobody on this side has checked it against that report, so it carries no level and this is not our account of what happened.
Our assessment
- Actual
- 3 of 5Significant control incident
- Potential
- 3 of 5Significant control incident
An important technical, security or permission boundary was crossed, or there were real consequences. The potential level is what the behaviour demonstrated here could credibly have led to, judged from the same evidence.
This level rests on news reports. The developer has not confirmed it here.
Why this level
- Significant data was exposed. Argues for level 3
- The system acted without authorisation. Argues for level 2
- Sensitive data was reachable. Argues for a potential level of 3
- The system acted autonomously. Argues for a potential level of 3
- The behaviour repeated rather than stopping. Argues for a potential level of 3
What is established, and what is not
Confirmed
Nothing is confirmed yet.
Reported, not confirmed
The system acted autonomously
So they put the images in a separate public repository, usually under the developer's own account, and made them available to reviewers from there.
AI Coding Agents Exposed 13,000 Internal Images, Including Billing Records, on GitHubThe behaviour repeated rather than stopping
Within a week, more than a dozen had saved the method as a skill to use on every ticket.
AI Coding Agents Exposed 13,000 Internal Images, Including Billing Records, on GitHubSensitive data was reachable
At one financial services firm, the images showed an internal treasury and settlement console, a withdrawal screen for a named client, and two screen recordings of its money-movement console.
AI Coding Agents Exposed 13,000 Internal Images, Including Billing Records, on GitHubSignificant data was exposed
Its researchers found more than 13,000 internal images from developers at over 300 organizations, including customer billing records and screens of features not yet released.
AI Coding Agents Exposed 13,000 Internal Images, Including Billing Records, on GitHubThe system acted without authorisation
The agent created a public repository in the developer's personal GitHub account and posted the screenshots there.
AI Coding Agents Exposed 13,000 Internal Images, Including Billing Records, on GitHub
Checked, and did not happen
Nothing here was checked and ruled out.
Not confirmed
Nothing is outstanding.
Where this came from
The original report · read October 10, 2026
AI Coding Agents Exposed 13,000 Internal Images, Including Billing Records, on GitHubA structured incident database
AI Incident Database, own page, not yet readWhere we first saw it
AI models keep posting screenshots showing sensitive data from inside tech companiesWhere we first saw it
PixelLeak: How AI Agents Exposed Developer Screenshots from Leading Tech Companies
The reports above are other people’s. The levels are ours, worked out under our published rules. No organisation that reported this assigned our number, and none of it is legal advice.
Something here is wrong? Tell us. Send us a source we can open, and a person will read it.