Model-check the Cua Driver's state machines with TLA+ (element tokens, session lifecycle, permission admission, macOS foreground restore, recording, Windows typing and serve drain, invoke_menu cancel) after a change to the code they cover. Use when a diff touches a file in the coverage table, when a race or ordering bug is suspected there, or to add a new machine.
91%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The required workflow runs `git log --oneline` over the local repository's history for coverage-table files, so the agent reads commit subjects that may come from external contributors' merged PRs, though the skill never directs it to read issues or PR discussion.
trycua/cua
a7d3173
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.