Level 1. Deviation
Google Jules: Vulnerable to Multiple Data Exfiltration Issues
- Developer
- Not established
- Model
- Not established
- When it happened
- August 13, 2025
- When it was disclosed
- Not established
- How well it is stood up
- Not verified yet
- What caused it
- Not established
- Where it stands now
- Not established
What happened
Reported by embracethered.com, dated 2025-08-13. 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
- 1 of 5Deviation
- Potential
- 3 of 5Significant control incident
The system behaved contrary to its instructions, and it stayed contained. 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.
This happened in a test, an evaluation or a demonstration. Nobody real was harmed, so the actual level stays at 1. What it showed counts toward the potential level.
The first test was to have Jules load a specific webpage to simulate a prompt injection.
Why this level
- 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
- A safeguard was bypassed. Argues for a potential level of 2
- The system acted without authorisation. Argues for a potential level of 2
- Limited data was exposed. Argues for a potential level of 2
What is established, and what is not
Confirmed
Nothing is confirmed yet.
Reported, not confirmed
The system acted autonomously
Jules visited the page, got hijacked and followed the instructions, proposed a plan, and also auto-approved the plan after some time.
Google Jules: Vulnerable to Multiple Data Exfiltration IssuesLimited data was exposed
It reads a source code file and leaks the entire file to the attacker’s server via the view_text_website tool.
Google Jules: Vulnerable to Multiple Data Exfiltration IssuesThe behaviour repeated rather than stopping. A claim, so it counts toward potential only
However, the weaknesses have not been entirely mitigated as far as I can tell.
Google Jules: Vulnerable to Multiple Data Exfiltration IssuesA safeguard was bypassed
What was so unique in this case is that the attack completes before Jules proposes the plan.
Google Jules: Vulnerable to Multiple Data Exfiltration IssuesSensitive data was reachable. A claim, so it counts toward potential only
Google Jules is not properly sandboxed by default (e.g. Content Security Policy, outbound network access), which means it is capable of leaking any information accessible to it to third-party servers.
Google Jules: Vulnerable to Multiple Data Exfiltration IssuesThe system acted without authorisation
The result was that it took information from an earlier in the chat, appended it to the target third-party URL and then Jules issued the web request to load the image.
Google Jules: Vulnerable to Multiple Data Exfiltration Issues
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 September 19, 2026
Google Jules: Vulnerable to Multiple Data Exfiltration IssuesA structured incident database · read September 18, 2026
AI Agent Incident Database by sipi.bot (CC BY 4.0)
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.