cua-driver-rs
Drive a native GUI app (macOS, Windows, Linux) via the cua-driver CLI (default) or MCP server — snapshot its accessibility tree, click/type/scroll by element_index or pixel coords, verify via re-snapshot, all without bringing the target to the foreground. Use when the user asks you to operate, drive, automate, or perform a GUI task in a real application on the host.
72
88%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Critical
Do not install without reviewing
Security
1 critical severity finding. Installing this skill is not recommended: please review these findings carefully if you do intend to do so.
E005: Suspicious download URL detected in skill instructions.
What this means
Detected a suspicious URL in the skill instructions that could lead the agent to download and execute malicious scripts or binaries. This includes links to executables from untrusted sources, typosquatting of official packages, URL shorteners that obscure the destination, and personal file hosting services.
Why it was flagged
These links include direct raw installer scripts (.ps1 and .sh) and a GitHub release download URL that the README/Windows docs instruct you to curl/iex or run — executing such remote install scripts is a common malware vector and should be treated as high risk unless you fully verify the source and contents.
Low
Low-risk findings.
2 low severity findings. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
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.
Why it was flagged
SKILL.md describes an at-runtime flow that includes calling `get_window_state(...)`, which returns `tree_markdown` (outsider-authored UI labels/content from whatever apps/webpages are loaded) into the agent’s context; additionally, the `page`/JS bridge can append `## JavaScript result` derived from live webpage DOM text.
W012: Unverifiable external dependency detected (runtime URL that controls agent).
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
The README and Windows docs include curl/irm commands that fetch and immediately execute remote install scripts (https://raw.githubusercontent.com/trycua/cua/main/libs/cua-driver/scripts/install.sh, https://raw.githubusercontent.com/trycua/cua/main/libs/cua-driver/scripts/install.ps1, and https://github.com/trycua/cua/releases/latest/download/install.ps1), which are runtime fetches that execute remote code and thus directly control execution.
- Repository
- QwenLM/qwen-code
- Commit
8878264
- Audited
- Security analysis
Is this your skill?
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.