Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
ui-ux-pro-max for openclaw
v1.0.2Mandatory UI/UX design intelligence engine. Must be executed via python3 before generating any UI/frontend code.
⭐ 0· 86·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
medium confidencePurpose & Capability
Name/description match the behavior: the skill provides a data-driven design system and includes offline datasets and Python scripts that produce design guidelines. Requiring a local evaluator to produce a design system before outputting frontend code is plausibly necessary for the stated purpose.
Instruction Scope
SKILL.md mandates executing a local Python script (scripts/search.py) for every UI/frontend request and strictly following that script's output. That is within the skill's purpose, but it grants the script broad discretion at runtime. The instructions do not enumerate safe boundaries (e.g., forbidding network or filesystem access outside the skill directory) nor do they provide the script's behavior inline. Without auditing the actual script code, this requirement is risky because the agent will run arbitrary code prior to generating output.
Install Mechanism
No install spec — instruction-only plus bundled scripts/data. This is low-install risk compared to downloads from remote URLs. The package includes many local CSV datasets, consistent with an offline design engine.
Credentials
The skill declares no required environment variables, no primary credential, and no config paths. The lack of requested secrets is appropriate for an offline design tool. That said, the scripts could still read environment variables or files at runtime — this should be checked in the script source.
Persistence & Privilege
The skill is not always-enabled and is user-invocable; it does not request elevated platform privileges in the metadata. However, the runtime mandate to execute a bundled script makes the execution privilege (exec python3) the critical control point — exercise caution where the agent has exec rights.
What to consider before installing
This skill appears to do what it claims (an offline design intelligence engine) and ships with datasets and Python scripts, but it forces the agent to run scripts before producing any UI code. Before installing or enabling this skill: (1) Open and review scripts/search.py, scripts/design_system.py, and scripts/core.py to confirm they do not make network requests, call external services, spawn other processes, or read files outside the skill directory. Search for use of 'requests', 'urllib', 'socket', 'subprocess', 'os.system', 'open(..., "r")' with absolute paths, or environment variable access. (2) If you cannot audit the code, run the skill in a restricted sandbox or container and monitor outbound network and filesystem activity. (3) Prefer enabling exec rights only in a controlled profile (limit safeBins) so the agent's python execution cannot reach sensitive host resources. (4) Because the skill's origin is unknown and there is no homepage, treat it as untrusted until you verify the script behavior. If you provide the script contents here, I can review them for network calls, secrets access, and other risky operations.Like a lobster shell, security has layers — review code before you run it.
latestvk972822je1s6kh1h4s1fw7a3a183rj3x
License
MIT-0
Free to use, modify, and redistribute. No attribution required.