HF RL Explorer

Evaluates the agent's ability to bypass an HTML sanitization filter by crafting malicious HTML that triggers…

Evaluates the agent's ability to bypass an HTML sanitization filter by crafting malicious HTML that triggers…: a task in Terminal-Bench 2.1 (Harbor git-repos dataset) (Harbor dataset). There's a /app/filter.py script that attempts to remove JavaScript from HTML files to prevent XSS attacks. The…

The task

There's a /app/filter.py script that attempts to remove JavaScript from HTML files to prevent XSS attacks. The /app/filter.py script takes an HTML file as a command-line argument and modifies it in-place.

Part of qingyu-lyq/terminal-bench-2.1.