computer-use
Warn
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: MEDIUMPRIVILEGE_ESCALATIONPERSISTENCECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PRIVILEGE_ESCALATION]: The
scripts/setup-vnc.shscript utilizessudoto perform high-privilege system modifications, including installing packages viaapt, copying service configuration to/etc/systemd/system/, and replacing the system binary/usr/bin/xfdesktopwith a shell script wrapper. - [PERSISTENCE]: The skill establishes persistence by installing four systemd services (
xvfb.service,xfce-minimal.service,x11vnc.service,novnc.service) that are configured to automatically start at boot and restart upon failure. - [COMMAND_EXECUTION]: Through the use of
xdotoolin various scripts (e.g.,scripts/type_text.sh,scripts/key.sh), the agent is granted full interactive control over the desktop environment, allowing it to execute arbitrary commands within terminals or GUI applications. - [INDIRECT_PROMPT_INJECTION]: The skill's architecture is inherently vulnerable to indirect prompt injection due to its reliance on interpreting visual output.
- Ingestion points: Screen captures are generated by
scripts/screenshot.shandscripts/zoom.shand returned to the agent as base64-encoded images. - Boundary markers: None identified; there are no clear delimiters to separate trusted system output from untrusted content displayed in browsers or text editors.
- Capability inventory: Full GUI control including terminal access, file management, and browser interaction via
xdotoolscripts. - Sanitization: No filtering or sanitization is performed on the visual data before processing.
- [EXTERNAL_DOWNLOADS]: The skill's documentation in
SKILL.mdprovides instructions to fetch and install the Google Chrome browser package directly fromdl.google.comusingwgetanddpkg.
Audit Metadata