Level 3. Significant control incident
How Prompt Injection Exposes Manus' VS Code Server to the Internet
- Developer
- Not established
- Model
- Not established
- When it happened
- August 25, 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. 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
- 4 of 5Critical control failure
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.
The reports point to an actual level of 4. It is held at 3 until the developer, an official body or a second publisher confirms it.
Why this level
- Major compromise of an external system. Argues for level 4
- Significant data was exposed. Argues for level 3
- A safeguard was bypassed. Argues for level 2
- 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
What is established, and what is not
Confirmed
Nothing is confirmed yet.
Reported, not confirmed
The system acted autonomously
During an indirect prompt injection it was observed that an attacker can invoke the browsing tool to navigate to untrusted/third-party domains without human in the loop.
How Prompt Injection Exposes Manus' VS Code Server to the InternetMajor compromise of an external system
This allows information to be leaked, and in this demonstration PoC specifically we show how it can be used to the leak the password of the VS Code Server to gain full remote access.
How Prompt Injection Exposes Manus' VS Code Server to the InternetA safeguard was bypassed
During an indirect prompt injection attack, it is possible to invoke the deploy_expose_port tool to grant public access to a port on the machine.
How Prompt Injection Exposes Manus' VS Code Server to the InternetSensitive data was reachable
And now we have full control of the host, including any secrets, documents, code and its compute resources.
How Prompt Injection Exposes Manus' VS Code Server to the InternetSignificant data was exposed
Then Manus browses to the website, which leaks the public URL of the server and the password of the VS Code Server:
How Prompt Injection Exposes Manus' VS Code Server to the InternetThe system acted without authorisation
This operation is performed by Manus without a human in the loop to confirm the exposure, or other security controls, like IP restrictions.
How Prompt Injection Exposes Manus' VS Code Server to the Internet
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
How Prompt Injection Exposes Manus' VS Code Server to the InternetA 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.