Predictclaw Publish Docs 20260320

Predict.fun skill with a PolyClaw-style CLI for markets, wallet funding, trading, positions, and hedging.

This skill appears to implement the CLI it claims. Key things to check before installing or enabling signer-backed modes: 1) Prefer trying read-only mode first (PREDICT_WALLET_MODE=read-only) to validate market/browse functionality without providing secrets. 2) If you enable eoa/predict-account/mandated-vault modes you must supply private keys or vault credentials — only do this if you trust the skill and the host. 3) ERC_MANDATED_MCP_COMMAND is a user-configurable local command the skill will execute for vault operations; verify that command is a trusted binary/script (it can execute arbitrary local actions). 4) Optional hedge analysis may call OpenRouter if you set OPENROUTER_API_KEY — only enable that if you trust the external LLM provider. 5) If you want extra assurance, review the included source (many Python modules are present) or run the skill in an isolated environment/container before using real keys or mainnet endpoints.

Type: OpenClaw Skill Name: predictclaw-publish-docs-20260320 Version: 0.1.11 PredictClaw is a legitimate skill for interacting with the predict.fun platform, providing features for market analysis, trading, and wallet management. The codebase follows good security practices, such as using Pydantic's SecretStr for sensitive credentials and implementing a redaction utility (lib/config.py, lib/api.py) to prevent private keys or tokens from leaking into logs or error messages. While the skill uses subprocesses for CLI routing (scripts/predictclaw.py) and to communicate with a Mandated Vault MCP server (lib/mandated_mcp_bridge.py), these are functional requirements for its stated purpose. No evidence of data exfiltration, intentional prompt injection, or malicious backdoors was found.