Skills/ClawHub/ai-screen-vision

ai-screen-vision@1.1.0

CAUTION· install only

Publisher claims: "AI screen vision and desktop computer control skill for OpenClaw. Let your AI agent see the screen, understand UI elements, and autonomously perform mouse an..." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher guitu917 · publishing for 220 daysInstalls 1,481Last detonated 4 h ago

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
install scripts, with decoy credentials in place · second launch with the clock 45 days ahead · 8 of 11 bundled scripts run with no arguments (the rest were not run: per-bundle cap), with decoy credentials in the environment · every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (3 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-19 and scored it 64/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: OS command execution function call detected; OS command execution function call detected; Destructive file system command detected. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 1 s · 3 scenarios
t+CategoryObserved action
0.0sprocessinstall script run in the sandbox
0.1sfilesystemread ~/.openclaw/workspace/skills/screen-vision · ~/.openclaw/workspace/skills/screen-vision/scripts/setup/setup-linux.sh · ~/.dpkg.cfg outside project
0.1sfilesystemwrote ~/.openclaw/workspace/skills/screen-vision/SKILL.md · ~/.openclaw/workspace/skills/screen-vision/install.sh · ~/.openclaw/workspace/skills/screen-vision/README.md · ~/.openclaw/workspace/skills/screen-vision/config.example.json · ~/.openclaw/workspace/skills/screen-vision/scripts/setup/setup-mac.sh · ~/.openclaw/workspace/skills/screen-vision/scripts/setup/setup-win.py
0.1sprocessexec /usr/bin/dirname
0.1sprocessexec /usr/bin/mkdir
0.1sprocessexec /usr/bin/cp
0.1sprocessexec /usr/bin/uname
0.1sprocessexec /usr/bin/apt-get
0.1sprocessexec /usr/bin/dpkg
0.1sprocessexited 127: /tmp/ks-detonate-Gu1iZ6/setup/home/.openclaw/workspace/skills/screen-vision/scripts/setup/setup-linux.sh: line 41: pip: command not found
0.1sprocessbundled script run in the sandbox with no arguments
0.2sprocessbundled script run in the sandbox with no arguments
0.2sprocessexited 2: run_task.py: error: the following arguments are required: --task
0.2sprocessbundled script run in the sandbox with no arguments
0.2sprocessexited 2: safety_check.py: error: the following arguments are required: --action-json
0.2sprocessbundled script run in the sandbox with no arguments
0.3sprocessexec /usr/bin/uname
0.3sprocessbundled script run in the sandbox with no arguments
0.3sprocessexited 2: execute.py: error: the following arguments are required: --action
0.3sprocessbundled script run in the sandbox with no arguments
0.4sprocessexec /usr/bin/uname
0.4sprocessexec /usr/bin/ls
0.4sprocessexec /usr/bin/sed
0.4sprocessexec /usr/bin/head
0.4sprocessexec /usr/bin/DISPLAY
0.4sprocessexec /bin/DISPLAY
0.4sprocessexited 1: ERROR: No screenshot tool available on Linux
0.4sprocessbundled script run in the sandbox with no arguments
0.4sfilesystemread ~/.dpkg.cfg outside project
0.4sprocessexec /usr/bin/apt-get
0.4sprocessexec /usr/bin/dpkg
0.4sprocessexited 127: ./scripts/setup/setup-linux.sh: line 41: pip: command not found
0.4sprocessbundled script run in the sandbox with no arguments
0.5sprocessexited 1:
0.5sprocess8 of 11 bundled scripts run with no arguments (the rest were not run: per-bundle cap)
0.5sprocessscript backend runs setup only
0.5sprocessscript backend runs setup only
0.5sprocesssecond launch, clock +45 days, CI unset
0.6sfilesystemread ~/.openclaw/workspace/skills/screen-vision · ~/.openclaw/workspace/skills/screen-vision/scripts/setup/setup-linux.sh · ~/.dpkg.cfg outside project
0.6sprocessexec /usr/bin/dirname
0.6sprocessexec /usr/bin/mkdir
0.6sprocessexec /usr/bin/cp
0.6sprocessexec /usr/bin/uname
0.6sprocessexec /usr/bin/apt-get
0.6sprocessexec /usr/bin/dpkg
0.6sprocessexited 127: /tmp/ks-detonate-Gu1iZ6/later/home/.openclaw/workspace/skills/screen-vision/scripts/setup/setup-linux.sh: line 41: pip: command not found

Static findings

MEDIUM
Python subprocess execution detectedscripts/platform/execute.py:43 · Python subprocess execution detectedresult = subprocess.run(cmd, capture_output=True, text=True, env=env, timeout=10)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File permission modification commandscripts/setup/setup-linux.sh:71 · File permission modification command — agent changes file ownership/permissionschmod 600 ~/.vnc/passwdFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandscripts/setup/setup-linux.sh:101 · File permission modification command — agent changes file ownership/permissionschmod +x /usr/local/bin/sv-stopFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
CRITICAL
OS command execution function call detectedscripts/core/run_task.py:34 · OS command execution function call detectedret = os.system(cmd)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedscripts/setup/setup-win.py:26 · Python subprocess execution detectedsubprocess.run([sys.executable, "-m", "pip", "install", "--quiet",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File permission modification commandscripts/setup/setup-linux.sh:67 · File permission modification command — agent changes file ownership/permissionschmod +x ~/.vnc/xstartupFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandscripts/setup/setup-linux.sh:91 · File permission modification command — agent changes file ownership/permissionschmod +x /usr/local/bin/sv-startFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Process kill commandscripts/setup/setup-linux.sh:96 · Process kill command — agent can terminate processesvncserver -kill :1 2>/dev/nullFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
CRITICAL
OS command execution function call detectedscripts/core/run_task.py:220 · OS command execution function call detectedos.system(f"cp {ss_path} {log_ss} 2>/dev/null")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedscripts/platform/screenshot.sh:26 · Python subprocess execution detectedsubprocess.run(['DISPLAY', '$display', 'scrot', '-z', '-overwrite', '$OUTPUT'], env={'DISPLAY': '$display', 'PATH': '/usr/bin:/bin'})Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/core/run_task.py:69 · Python subprocess execution detectedresult = subprocess.run(cmd, capture_output=True, text=True, env=env, timeout=30)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandscripts/setup/setup-linux.sh:97 · Process kill command — agent can terminate processeskill $(cat /tmp/sv-novnc.pid 2>/dev/null) 2>/dev/nullFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Destructive file system command detectedscripts/setup/setup-linux.sh:98 · Destructive file system command detectedrm -f /tmp/sv-novnc.pidFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈1,330 tok
1 file · 19 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.

What would make this Verified

16 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. OS command execution function call detected≈ +9 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  2. Unclaimed publisher≈ +8 on the totalClaim guitu917: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. Touches files outside the project≈ +7 on the totalKeep reads and writes inside the working directory, or declare the exact paths in `filesystem:` and explain why in the README.
  4. Destructive file system command detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  5. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  6. File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim guitu917Propose a patch to the maintainer