Manifold Markets

PassAudited by VirusTotal on May 12, 2026.

Overview

Type: OpenClaw Skill Name: manifold Version: 1.0.0 The skill is benign. It clearly defines its purpose to interact with Manifold Markets via their official API. It explicitly instructs the AI agent to obtain user confirmation for all write actions (placing bets, selling shares, posting comments), which is a strong safeguard against prompt injection. The `MANIFOLD_API_KEY` is used solely for authentication with the legitimate `api.manifold.markets` endpoint, and there is no evidence of data exfiltration, malicious execution (e.g., `curl|bash`), persistence mechanisms, or obfuscation techniques. All commands are standard `curl` requests or `jq` for local JSON parsing.

Findings (0)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

What this means

If used incorrectly, the agent could change your Manifold positions or post comments, but the documented workflow requires confirmation first.

Why it was flagged

The skill can perform mutating Manifold actions, but the artifact explicitly requires user confirmation before those actions.

Skill content
Never place a bet, sell shares, or post a comment unless the user explicitly confirms
Recommendation

Only confirm bets, sells, or comments after checking the market, side, amount or shares, and exact comment text.

What this means

Anyone using this skill with your API key can act on your Manifold account within the API key’s permissions.

Why it was flagged

The Manifold API key delegates account authority to the agent for authenticated actions such as placing bets, selling shares, and commenting.

Skill content
Uses `MANIFOLD_API_KEY` in header: `Authorization: Key $MANIFOLD_API_KEY`
Recommendation

Use a dedicated or revocable Manifold API key if possible, keep it out of shared logs, and revoke it if you no longer use the skill.