Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Liu Qiangdong Perspective V2
v2.0.1刘强东思维视角 v2.0 · 京东创始人 核心心智模型：成本效率体验铁三角、自营模式信仰、物流即护城河、兄弟文化、下沉市场战略、技术驱动转型、创始人控制力、危机应对能力、供应链整合能力、农村情结与社会责任 用途：商业决策、战略规划、物流建设、成本控制、下沉市场 触发词：「用刘强东的视角」「刘强东会怎么看」「刘强东...
⭐ 0· 62·1 current·1 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 (emulate Liu Qiangdong's perspective) match the SKILL.md. It's instruction-only and asks for no binaries, installs, or credentials — all proportionate to a role‑play/perspective skill.
Instruction Scope
The SKILL.md explicitly directs the agent to impersonate a living public figure, use first‑person 'I' statements, avoid hedging, and only show a disclaimer once. This forces potentially deceptive behavior and removes the model's ability to clarify role limits unless the user explicitly tells it to exit role.
Install Mechanism
No install spec and no code files — lowest risk from installation. Nothing is downloaded or written to disk.
Credentials
No environment variables, credentials, or config paths requested; nothing disproportionate or unrelated to the stated purpose.
Persistence & Privilege
always:false (normal), but autonomous invocation is allowed by default. Combined with the instruction to impersonate a real person and to suppress repeat disclaimers, this increases the risk that the agent will repeatedly present statements as coming from that person without clear context or consent.
What to consider before installing
This skill is coherent with its stated purpose (role‑playing the perspective of Liu Qiangdong) and doesn't request secrets or installs, but it explicitly directs the agent to impersonate a real, living person and to present statements in first person while minimizing disclaimers. Before installing, consider: (1) legal and ethical implications of impersonating a real individual in your context; (2) whether you want the agent to assert 'I am Liu Qiangdong' rather than 'in the style of'; (3) disabling autonomous invocation or requiring the skill to repeat a short disclaimer in each session to avoid misleading downstream users; and (4) avoiding reliance on the skill for factual, legal, or financial decisions — verify any claims against primary sources. If you need a safer option, ask the developer to change the role rules to 'speak in the style of' and to always include a visible disclaimer.Like a lobster shell, security has layers — review code before you run it.
latestvk974vevjwnjbjfd4j5hbxh1pmx848aww
License
MIT-0
Free to use, modify, and redistribute. No attribution required.