Stock Picker Orchestrator

Acts as a meta-orchestrator that routes stock-analysis requests across data, macro/news, and valuation skills under explicit budget controls; used when users...

This skill is an instruction-only orchestrator and appears coherent with its purpose, but it delegates all network access and credential use to the downstream skills it names (vnstock-free-expert, news/macro monitors, equity-valuation-framework, etc.). Before installing or invoking it: 1) verify those dependent skills are trustworthy and review their required env vars/API keys; 2) test the orchestrator in a safe environment to confirm budget limits behave as expected; 3) if you need tighter control, restrict autonomous invocation or require explicit user approval before running high-budget/deep pipelines; and 4) note that absence of code meant the static scanner had nothing to analyze — that reduces installer risk but also means you should inspect the workspace for the named skills' behavior and endpoints.

Type: OpenClaw Skill Name: stock-picker-orchestrator Version: 1.0.2 The skill bundle is benign. Both `SKILL.md` and `agents/openai.yaml` consistently instruct the AI agent to operate with transparency, strict budget controls (e.g., API call limits, free-tier pacing), and responsible reporting (mandatory output contract, confidence rubric). It explicitly warns against presenting uncertain outputs as facts, self-modifying user data, or providing absolute buy/sell instructions. There is no evidence of prompt injection attempts to subvert the agent's behavior, exfiltrate data, execute arbitrary commands, or establish persistence. The instructions actively promote ethical and cautious AI behavior.