Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
接送机服务
v1.0.0企业用车服务助手，支持即时用车、预约用车、接送机、包车等多种用车场景，提供车型选择、费用预估、订单管理等功能。Invoke when user needs to book a car, schedule a ride, airport transfer, or manage car service orders.
⭐ 0· 32·0 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 and description (airport transfer / car service) match the included code (ride ordering, price estimation, booking). However SKILL.md explicitly requires calling a "real用车平台API" to get prices/vehicles, while the shipped Python code (car_service_api.py and openai_adapter.py) uses local simulated driver and airport data and random distance calculation. The presence of both the requirement and only a simulator is an incoherence: either the skill is an emulator (docs inaccurate) or it expects additional integration/credentials that are not declared.
Instruction Scope
SKILL.md scopes functionality to booking/estimates/orders and does not request arbitrary system access, which is good. But a prompt‑injection pattern (unicode control chars) was flagged in the SKILL.md and the doc includes a mandatory constraint to call real platform APIs; the instructions therefore conflict with the provided code and may attempt to influence LLM behavior. No instructions ask to read unrelated files or exfiltrate data, but the mismatch in required external integration is concerning.
Install Mechanism
There is no install spec (instruction-only). The only runtime dependency is python3, which is reasonable for the provided Python scripts. No external downloads or archive extraction are present in the metadata.
Credentials
SKILL.md states the skill must call a real platform API (which would normally require API keys/credentials), but the skill declares no required environment variables, no primary credential, and the code contains no API key handling. This mismatch is disproportionate: either credentials are omitted from the metadata or the doc's requirement is misleading.
Persistence & Privilege
The skill is not always-enabled (always:false), is user-invocable, and does not request elevated privileges or modify other skills. There is no indication it persists sensitive data or alters agent-wide config.
Scan Findings in Context
[unicode-control-chars] unexpected: A unicode control character pattern was detected in SKILL.md. This is not expected for a straightforward ride‑booking skill and can be used to influence or obfuscate LLM behavior; treat as suspicious and ask the author to remove/justify it.
What to consider before installing
Do not install blindly. Ask the publisher to clarify whether this is a simulator or a production integration: if it must call a real ride‑platform API, the skill should declare which API and what environment variables (API keys/tokens) it needs. Review the Python files yourself (or have a developer do so) to confirm there are no hidden network calls or hardcoded endpoints before providing credentials. Because SKILL.md contains a prompt‑injection marker, prefer running the code in a sandboxed environment first and confirm the skill does not reach out to unexpected external servers. If you need production integration, request that the author add explicit env var requirements and documentation of how credentials are used.Like a lobster shell, security has layers — review code before you run it.
latestvk973gayntw1z6gm0dx7g3akabn83yvpr
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
🚗 Clawdis
Binspython3