← Back to Skills Marketplace
Prediction Bridge Skill
by
kimCheese888
· GitHub ↗
· v1.0.0
802
Downloads
2
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install prediction-bridge
Description
Query live prediction market data from the Prediction Bridge API. Use when the user asks about prediction markets, event odds, market prices, whale trades, trader analytics, or news related to prediction markets. Provides semantic search across 9+ platforms (Polymarket, Kalshi, Limitless, Probable, PredictFun, SxBet, Myriad, PancakeSwap), on-chain whale trade monitoring, Smart PnL analytics, and trader leaderboards. Run the bundled Python script to fetch real-time data.
Usage Guidance
This skill appears internally consistent: the script does what the README says and does not ask for credentials. However the default API host (prediction-bridge.onrender.com) and the skill owner are unverified (no homepage). Before installing or using it with sensitive input: (1) review the full script (it is included) and confirm you are comfortable with network calls to the default endpoint, (2) do not submit private keys, passwords, or other secrets through the CLI, (3) if you want more assurance, run the script against a self-hosted/trusted proxy by setting PREDICTION_BRIDGE_URL to a vetted endpoint or run it in a sandbox, and (4) prefer skills with a named publisher and homepage for production use.
Capability Analysis
Type: OpenClaw Skill
Name: prediction-bridge
Version: 1.0.0
The skill bundle itself does not contain explicitly malicious code. However, it presents two significant vulnerabilities. Firstly, the `SKILL.md` instructs the OpenClaw agent to execute `python scripts/prediction_bridge.py` with user-provided arguments. If the agent does not properly shell-escape these arguments, it creates a critical shell injection (RCE) vulnerability. Secondly, the `scripts/prediction_bridge.py` script allows overriding the `PREDICTION_BRIDGE_URL` via an environment variable, which, if controllable by an attacker (e.g., through prompt injection against the agent), could lead to Server-Side Request Forgery (SSRF) by redirecting API calls to an arbitrary endpoint. These are vulnerabilities in the agent's interaction with the skill, not direct malicious intent within the skill's code.
Capability Assessment
Purpose & Capability
Name/description match the bundled CLI Python client. The code implements the commands described (search, events, whale-trades, analytics, etc.) and only makes HTTP requests to the configured API; there are no unrelated capabilities (no cloud SDKs, no database or OS-level access).
Instruction Scope
SKILL.md instructs running the included Python script; the script uses only stdlib and issues GET/POST requests to the API. It does not read arbitrary local files or request other environment variables beyond an optional PREDICTION_BRIDGE_URL. Note: user queries, wallet addresses, and market IDs supplied to the CLI will be transmitted to the remote API.
Install Mechanism
There is no install spec — instruction-only with an included script. No archives or remote installers are fetched during install. Risk from install mechanism is low.
Credentials
The skill does not require credentials or special environment variables; only an optional PREDICTION_BRIDGE_URL override is documented. No unexpected secrets or unrelated env vars are requested.
Persistence & Privilege
always is false and the skill does not attempt to modify other skills or system configs. The skill can be invoked autonomously by the agent (platform default) which will cause network calls if used — this is normal but worth noting.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install prediction-bridge - After installation, invoke the skill by name or use
/prediction-bridge - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of Prediction Bridge skill.
- Query real-time prediction market data from 9+ platforms via the Prediction Bridge API.
- Supports commands for semantic event search, listing events, market prices, whale trades, analytics, trader leaderboards, and news.
- Provides detailed command-line instructions and typical use cases.
- No external Python dependencies required; works with standard library only.
Metadata
Frequently Asked Questions
What is Prediction Bridge Skill?
Query live prediction market data from the Prediction Bridge API. Use when the user asks about prediction markets, event odds, market prices, whale trades, trader analytics, or news related to prediction markets. Provides semantic search across 9+ platforms (Polymarket, Kalshi, Limitless, Probable, PredictFun, SxBet, Myriad, PancakeSwap), on-chain whale trade monitoring, Smart PnL analytics, and trader leaderboards. Run the bundled Python script to fetch real-time data. It is an AI Agent Skill for Claude Code / OpenClaw, with 802 downloads so far.
How do I install Prediction Bridge Skill?
Run "/install prediction-bridge" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Prediction Bridge Skill free?
Yes, Prediction Bridge Skill is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Prediction Bridge Skill support?
Prediction Bridge Skill is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Prediction Bridge Skill?
It is built and maintained by kimCheese888 (@kimcheese888); the current version is v1.0.0.
More Skills