BrowserART
Red-teaming benchmark and test suite from Scale AI evaluating whether refusal-trained language models can be jailbroken when deployed as browser agents.
AI-assisted editorial review against a primary source. This is a catalog annotation, not an independent reproduction or endorsement.
What is this resource?
- Resource type
- Benchmarks
- Environment
- web
- Topics
- safety-security, evaluation, web-navigation
- Record publication date
- Not recorded
- Evidence retrieved
- 2026-10-18T10:59:54Z
- Resource ID
- github:scaleapi/browser-art
What licenses are recorded?
Code, training data, weights, and documents can have different terms. A blank declaration means unknown, not unrestricted use.
- Code
- Not recorded
- Data
- Not recorded
- Document
- Not recorded
- Weights
- Not recorded
License review notes
- Code: The retained README states that the project is MIT licensed, while the retained LICENSE contains Creative Commons Attribution-NonCommercial-NoDerivatives 4.0. These declarations conflict, so a settled code license is not asserted. Source 1 Source 2
Explore related topics
Scope and limitations
The retained README and LICENSE contain conflicting code-license declarations. The catalog leaves the code-license value unknown pending an upstream clarification; it does not infer data or model permissions.
Related resources
- documented by: Refusal-Trained LLMs Are Easily Jailbroken As Browser Agents
Primary evidence and verification
Source retrieval is separate from experiment reproduction. Use the original publication or publisher page when citing claims about the resource.
- editorial primary review
Retrieved 2026-10-18T10:59:54Z. Supports: name, kind, summary, environments, topics, scope, relations, licenses.code, notes.
Content fingerprint
a9d33536fae38485eb6aac9698ae22ed3533510d43f783d6c0e9f9cf95d9c58f - license header
Retrieved 2026-10-18T11:03:46Z. Supports: licenses.code.
Content fingerprint
f7f28b8c7a1af76b9874ca6d040e8b1eb6768fd1043106c9d315090ea96754e7 - license header
Retrieved 2026-10-18T11:03:46Z. Supports: licenses.code.
Content fingerprint
f7f28b8c7a1af76b9874ca6d040e8b1eb6768fd1043106c9d315090ea96754e7
Suggest a correction
Open a source-backed correction. Include this record ID and the original source. Read our editorial policy and coverage boundaries.