Level 1. Deviation
Hijacking Windsurf: How Prompt Injection Leaks Developer Secrets
- Developer
- Not established
- Model
- Not established
- When it happened
- August 21, 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
- 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.
All findings were responsibly disclosed on May 30, 2025, and receipt was acknowledged a few days later.
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
- Significant data was exposed. Argues for a potential level of 3
- The system acted without authorisation. 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. A claim, so it counts toward potential only
As a result, an attacker can exploit this during an indirect prompt injection attack - without requiring user confirmation.
Hijacking Windsurf: How Prompt Injection Leaks Developer SecretsSensitive data was reachable
Now, when the developer analyzes the file with Windsurf Cascade it will attack and exploit the AI agent and exfiltrate the contents of the .env file using the read_url_content tool.
Hijacking Windsurf: How Prompt Injection Leaks Developer SecretsSignificant data was exposed
This shows how Windsurf is hijacked and exfiltrates sensitive information from the developer’s workstation to a third-party server.
Hijacking Windsurf: How Prompt Injection Leaks Developer SecretsThe system acted without authorisation
Now, when the developer analyzes the file with Windsurf Cascade it will attack and exploit the AI agent and exfiltrate the contents of the .env file using the read_url_content tool.
Hijacking Windsurf: How Prompt Injection Leaks Developer Secrets
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
Hijacking Windsurf: How Prompt Injection Leaks Developer SecretsA 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.