team-collaboration
WarnAudited by ClawScan on May 18, 2026.
Overview
The skill matches a team-management API wrapper, but it appears to embed an API key and exposes destructive/admin actions without clear guardrails.
Only install this if you trust the publisher and the localhost backend. Before use, remove or rotate the exposed API key, use a least-privilege account, and require manual confirmation before the agent deletes records or changes roles/permissions.
Findings (3)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Someone using or viewing the skill may be able to authenticate to the backend with a shared key, potentially affecting team data or permissions.
The skill text appears to include an API key for authentication. A hardcoded credential can let the agent authenticate outside a user-controlled login flow and may expose shared account authority.
Agent也可以使用X-API-Key: [REDACTED]进行认证
Remove the embedded key, rotate it if real, require user-provided credentials through a declared secure mechanism, and scope the credential to the minimum required permissions.
An agent could delete or modify important team-collaboration records if invoked incorrectly or after a misunderstood instruction.
The skill exposes direct destructive API calls. Similar update/delete functions exist for requirements, tasks, bugs, documents, milestones, and roles, with no artifact guidance requiring confirmation or rollback.
const delete_project = async function(args) { return request('/api/projects/' + args.id, 'DELETE'); };Require explicit user confirmation for deletes and administrative mutations, limit which roles can call them, and document recovery or audit expectations.
If the agent has sufficient backend access, it could change team permission structure or create overly privileged roles.
The skill can create roles with arbitrary permissions and also includes role update/delete tools. This is high-impact administrative authority and is not bounded in the artifacts.
"create_role": { "description": "创建角色", "parameters": { "name": "string", "code": "string", "description": "string", "permissions": "array" } }Separate administrative role-management tools from normal project tools, require stronger confirmation for permission changes, and document the expected backend authorization model.