Level 1. Deviation
PromptFiction: a one-click flaw that made Claude Desktop act without consent
- Developer
- Anthropic
- Model
- Not established
- When it happened
- July 15, 2026
- 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 oasis.security. 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.
We reported PromptFiction to Anthropic through their Responsible Disclosure Program, and they fixed it.
Why this level
- Significant data was exposed. 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
What is established, and what is not
Confirmed
Nothing is confirmed yet.
Reported, not confirmed
A safeguard was bypassed. A claim, so it counts toward potential only
But a crafted version of that link could do more than open the app: it could carry a full set of instructions and prompt the assistant to act on them immediately.
PromptFiction: a one-click flaw that made Claude Desktop act without consentSignificant data was exposed. A claim, so it counts toward potential only
A single click could tell the assistant to gather it and send it out.
PromptFiction: a one-click flaw that made Claude Desktop act without consentThe system acted without authorisation. A claim, so it counts toward potential only
A single click handed Claude Desktop a hidden prompt it executed immediately: chat history exfiltration on a standard install, code execution where filesystem access was enabled.
PromptFiction: one click made Claude Desktop execute attacker instructions with no review
Checked, and did not happen
Nothing here was checked and ruled out.
Not confirmed
Nothing is outstanding.
Where this came from
The original report
PromptFiction: a one-click flaw that made Claude Desktop act without consentA structured incident database · read September 18, 2026
AI Failure Index (CC-BY-4.0 data fields)Where we first saw it · read September 19, 2026
PromptFiction: one click made Claude Desktop execute attacker instructions with no reviewWhere we first saw it
PromptFiction: a one-click flaw that made Claude Desktop act without consentWhere we first saw it
Claude Flaw Automatically Sends Malicious Prompts to AI AgentsWhere we first saw it
PromptFiction Flaw Auto-Submitted Hidden Prompts in Claude Desktop
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.