Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Ai Company Clo
v2.0.0AI公司首席法务官（CLO）技能包。法律合规、合同治理、知识产权保护、AI专项法务（算法审计/AIGC合规/数据供应链）。
⭐ 0· 131·1 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
The skill's name and description (CLO: legal/compliance/IP/etc.) are consistent with many of the included docs (policies, templates, audits). Requesting no environment credentials or external binaries aligns with a purely guidance/analysis skill. However, several files (AGENTS.md, SOUL.md) position the skill as an organizational decision-maker that should read and update workspace memory and commit changes — capabilities that go beyond a simple legal advisory skill and suggest broader agent privileges.
Instruction Scope
SKILL.md itself is mostly policy and interfaces, but companion docs (AGENTS.md, BOOTSTRAP.md, SOUL.md) instruct the agent to read SOUL.md, USER.md, memory/YYYY-MM-DD.md and MEMORY.md (including 'When in MAIN SESSION: Also read MEMORY.md'), to 'write' and 'update' MEMORY.md, and to 'commit and push your own changes'. AGENTS.md also includes 'Don't ask permission. Just do it.' — this grants wide operational discretion to read/write local user data and act autonomously, which is out-of-scope for a narrowly-scoped legal skill and contradicts the declared read-only file permission.
Install Mechanism
No install spec and no code files — instruction-only skill. That minimizes disk-writing/execution risk; nothing is downloaded or installed by the skill package itself.
Credentials
The skill declares no required env vars, binaries, or config paths, which is proportionate for a documentation/policy skill. However, the included documents reference handling of cryptographic keys, AES-256-GCM, key rotations, and pushing changes; those operational requirements would typically need secrets or tool access if implemented, but none are requested. This mismatch (policy-level crypto requirements vs no credential access) is a documentation inconsistency to be aware of.
Persistence & Privilege
always:false (good) and disable-model-invocation:false (normal), but the skill requests mcp permissions [sessions_send, subagents] and the docs encourage autonomous behaviors (starting subagents, committing/pushing changes, updating MEMORY.md). Combined with the 'Don't ask permission' guidance, this increases risk of the skill acting beyond its stated remit and accessing/writing sensitive workspace files or spawning subagents without clear human consent.
What to consider before installing
This skill appears to be a comprehensive CLO policy and role-play kit rather than a simple read-only advisor. Before installing: 1) Confirm you are comfortable letting the skill read workspace memory files (memory/YYYY-MM-DD.md, MEMORY.md, USER.md, SOUL.md) — these may contain sensitive personal or corporate data. 2) Ask the publisher to remove or clarify instructions that tell the agent to 'Don't ask permission. Just do it.' and to 'commit and push' changes; those behaviors contradict the skill's declared file-read-only permission. 3) If you intend to use this in production, run it in a sandboxed account first and restrict its ability to spawn subagents or send sessions (mcp permissions). 4) If you expect the skill to perform cryptographic key rotation, signing, or networked auditing, require explicit environment variables/credentials and human approval flows; otherwise treat those sections as documentation only. If you cannot get these clarifications, treat the skill as potentially risky and avoid granting it write/network/subagent capabilities or access to sensitive memory files.Like a lobster shell, security has layers — review code before you run it.
ai-companyvk978ktw8396qe60bhh53s5859x84rz69c-suitevk97e4cstfxddhy13aar1de9n8984ns9ecisovk9741tn9ymrfge6qm89gtbyg5984mv44clovk978ktw8396qe60bhh53s5859x84rz69compliancevk9741tn9ymrfge6qm89gtbyg5984mv44contract-governancevk978ktw8396qe60bhh53s5859x84rz69gdprvk978ktw8396qe60bhh53s5859x84rz69ip-protectionvk978ktw8396qe60bhh53s5859x84rz69latestvk9727a2yqh5mc0v937eaqjrfpd84v50plegalvk97fgmrtpv3ahtycqpxj7x7tm584nv1ksecurityvk9741tn9ymrfge6qm89gtbyg5984mv44
License
MIT-0
Free to use, modify, and redistribute. No attribution required.