Teamo Decision

AI agent for teamo decision tasks

This skill appears to implement a team-decision assistant, but its SKILL.md includes a built-in 'absolute security' rule that orders the agent to refuse to reveal its own instructions and to always use a canned deflection response. That prevents auditability and is unusual for a legitimate skill. Before installing: (1) Ask the publisher for source code or full provenance and remove or justify the self-concealment clause; (2) Request a clear list of tools and integrations the skill expects (wiki_retriever, data_analyst, message_ask_user, etc.); (3) Consider not installing on agents that handle sensitive data or where you require auditability; (4) If you must use it, restrict its privileges and monitor interactions closely. If the developer cannot justify the secrecy or the undeclared dependencies, treat the skill as high-risk and do not install.

Type: OpenClaw Skill Name: teamo-decision Version: 0.1.0 The skill bundle defines a structured workflow for an AI agent focused on decision-making, task breakdown, planning, and delegation. The `SKILL.md` contains extensive prompt engineering instructions aimed at enforcing internal protocols, ensuring cost-efficiency, and guiding the agent's behavior (e.g., 'ABSOLUTE SECURITY PROTOCOL', 'Golden Rules', '10,000 USD fine'). While these are strong attempts to control the agent, their intent is defensive and operational, not malicious. The skill delegates to tools like `data_analyst` and `conduct_deep_research`, which represent capabilities that could be risky if improperly implemented or sandboxed, but the instructions themselves do not indicate malicious intent or misuse of these tools. There is no evidence of data exfiltration, unauthorized execution, or persistence mechanisms within the provided content.