brin
brin

cua-agent

PyPI

Is cua-agent safe to use?

Based on the latest brin safety scan, no vulnerabilities or threats were detected for cua-agent v0.7.26. Trust score: 60/100. No known CVE vulnerabilities, no detected threat patterns, and no suspicious capabilities identified. This is an automated, point-in-time assessment.

Install (safety-checked)

cua-agent Passed Security Checks

No security concerns detected

clean
CVEs

0

Threats

0

Install Scripts

0

No Concerns Detected

No security concerns detected in the latest brin assessment. This is an automated, point-in-time evaluation — security posture may change.

This is an automated, point-in-time assessment and may contain errors. Findings are risk indicators, not confirmed threats. Security posture may change over time. Maintainers can dispute findings via the brin review process.

cua-agent Capabilities & Permissions

What cua-agent can access when installed. Review these capabilities before using with AI agents like Cursor, Claude Code, or Codex.

Network Access

This package makes network requests.

arxiv.orgcua.aifoundry-inference-xxx.centralus.inference.ml.azure.comgithub.comhuggingface.coinference.cua.aim-linux-96lcxd2c2k.containers.cloud.trycua.complatform.claude.comupload.wikimedia.orgwww.google.com
Protocols: http, https, tcp

Filesystem Access

Reads and writes to the filesystem.

.env (r).env (rw)/usr/ (rw).env (rw).env (rw).env (rw).env (rw).env (rw)

Process Spawning

This package can spawn child processes.

Environment Variables

Accesses the following environment variables.

ANTHROPIC_API_KEYCUA_API_KEYCUA_BASE_URLCUA_CONTAINER_NAMECUA_INFERENCE_API_KEYGOOGLE_API_KEYGOOGLE_CLOUD_PROJECTHUMAN_BASE_URLOPENAI_API_KEYSPECIAL_CODE_MODE+2 more

Native Modules

Contains native code that runs outside the JavaScript sandbox.

ctypes

AGENTS.md for cua-agent

Good instructions lead to good results. brin adds cua-agent documentation to your AGENTS.md so your agent knows how to use it properly—improving both safety and performance.

brin init

Vercel's research: 100% accuracy with AGENTS.md vs 53% without →

cua-agent Documentation & Source Code

For the full cua-agent README, API documentation, and source code, visit the official package registry.

View on PyPI

Frequently asked questions about cua-agent safety

Weekly Downloads

11.9K

Version

0.7.26

Other Versions

0.7.25

Last Scanned

3 days ago

Trust Score

60/100·Legitimacy signals, not safety

Capabilities

Network

Connects to: arxiv.org, cua.ai, foundry-inference-xxx.centralus.inference.ml.azure.com...

Filesystem

Reads & Writes files

Process

Spawns child processes

Environment

Accesses: ANTHROPIC_API_KEY, CUA_API_KEY, CUA_BASE_URL...

Native

Contains native modules