Install
$ agentstack add skill-nutdnuy-webull-openapi-ai-plugin-webull-watchlists ✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README — it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming — see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps — measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Webull watchlists
Read the relevant object in references/endpoints.json, follow its schema_ref into references/openapi.json, and read references/authentication.md before building parameters or JSON. Consult the official Webull Open API reference.
First-use onboarding
Before the first watchlist request, check for WEBULL_APP_KEY and WEBULL_APP_SECRET in the secure environment. If the API Key is missing, ask the user to configure it securely and stop. Never ask the user to paste the App Secret or access token into chat.
Supported endpoints
GET /openapi/market-data/watchlist/list— read-only list.POST /openapi/market-data/watchlist/createPOST /openapi/market-data/watchlist/updatePOST /openapi/market-data/watchlist/deleteGET /openapi/market-data/watchlist/instruments/list— read-only instrument list.POST /openapi/market-data/watchlist/instruments/addPOST /openapi/market-data/watchlist/instruments/updatePOST /openapi/market-data/watchlist/instruments/remove
All paths are documented in the official reference index.
Workflow and confirmation gate
- Use the catalog entry to determine the exact method, identifiers, parameter placement, and body schema. Do not reuse a body between watchlist endpoints or invent a watchlist id.
- Execute read-only list calls directly when authorized:
``bash python scripts/webull_api.py request --method GET --path /openapi/market-data/watchlist/list python scripts/webull_api.py request --method GET --path /openapi/market-data/watchlist/instruments/list --query-json '{"watchlist_id":""}' ``
- For every write path, first summarize the exact endpoint, target watchlist/instrument, and redacted request body. Ask for explicit confirmation immediately before the call. A request to “show”, “review”, or “find” a watchlist never authorizes a write.
- After confirmation, invoke the catalog-shaped request, for example:
``bash python scripts/webull_api.py request --method POST --path /openapi/market-data/watchlist/create --body-file ./watchlist-create.json --allow-write --write-confirmation WATCHLIST_WRITE ``
- Report the response and any returned identifiers. Never expose secrets, and never turn a watchlist change into an order or investment recommendation.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: nutdnuy
- Source: nutdnuy/webull-openapi-AI-Plugin
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet — be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.