US Stock Analyst by leading AI LLM models with Bloomberg Data, Twitter Sentiment and Wall Street Equity Research Reports

Professional US stock analysis with financial data, news, social sentiment, and multi-model AI. Comprehensive reports at $0.02-0.10 per analysis.

This package appears internally consistent and implements what it claims: it uses a single AIsa API key to fetch financial data, social signals, and to call an LLM gateway. Before installing or running: 1) Verify and trust the AIsa provider (https://aisa.one) because all data, prompts, and any sensitive input will be sent to that service. 2) Use a dedicated API key with limited credits/quotas to avoid unexpected charges or broad access. 3) Inspect the included Python scripts (they are plain-text) and run them in a sandbox or non-production environment first — they make outbound HTTPS calls and save reports locally. 4) Be aware the package omits a LICENSE in the release notes (legal/redistribution concern). 5) If you need Bloomberg-sourced raw data or vendor-level guarantees, confirm with the provider — the skill's marketing mentions Bloomberg but the code only calls AIsa endpoints that may aggregate third-party sources. If any of these points are unacceptable, do not install or run with keys containing privileged access.

Type: OpenClaw Skill Name: openclaw-aisa-us-stock-analyst Version: 1.0.1 The OpenClaw AgentSkills skill bundle for 'us-stock-analyst' is benign. The Python scripts (`stock_analyst.py`, `basic_analysis.py`, `batch_analysis.py`, `deep_analysis.py`, `test_api_data.py`) and documentation (`SKILL.md`, `README.md`, `TEST_REPORT.md`) are consistent with the stated purpose of providing stock analysis using the AIsa API. The skill correctly retrieves an API key from environment variables, makes HTTP requests to the documented `api.aisa.one` endpoints, and saves analysis reports to the local filesystem, all for legitimate purposes. There is no evidence of data exfiltration to unauthorized endpoints, malicious execution, persistence mechanisms, obfuscation, or prompt injection attempts against the OpenClaw agent itself. The prompts constructed for external LLMs are for legitimate analytical tasks, not for subverting the agent.