Prediction Market Trader

AdvisoryAudited by Static analysis on Apr 30, 2026.

Overview

No suspicious patterns detected.

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.

ConcernHigh Confidence

ASI03: Identity and Privilege Abuse

What this means

Running the skill with a broadly privileged Kalshi key could allow account reads and trades using the user’s real account.

Why it was flagged

The included code requires a Kalshi key ID and RSA private key, while the registry metadata declares no required environment variables or primary credential. These credentials can authenticate to a financial trading account.

Skill content

const keyId = process.env.KALSHI_KEY_ID;
const privKey = process.env.KALSHI_PRIVATE_KEY;
if (!keyId || !privKey) throw new Error('Set KALSHI_KEY_ID and KALSHI_PRIVATE_KEY env vars');

Recommendation

Declare the Kalshi credentials in metadata, document the required key scope, use read-only credentials for scanning where possible, and require a separate explicit trading credential for order placement.

ConcernHigh Confidence

ASI02: Tool Misuse and Exploitation

What this means

A mistaken or over-eager agent could place or cancel real Kalshi orders and cause financial loss.

Why it was flagged

The API client exposes direct order placement and cancellation with caller-supplied ticker, side, count, and price, but the included function does not enforce dry-run mode, user confirmation, bankroll limits, edge thresholds, or duplicate-position checks.

Skill content

async function placeOrder({ ticker, action = 'buy', side = 'yes', type = 'limit', count, price }) {
  return kalshiApi('POST', '/trade-api/v2/portfolio/orders', {
    ticker, action, side, type, count,
    yes_price: side === 'yes' ? price : undefined,
    no_price: side === 'no' ? price : undefined,
  });
}

async function cancelOrder(orderId) {
  return kalshiApi('DELETE', '/trade-api/v2/portfolio/orders/' + orderId);
}

Recommendation

Add hard safeguards in executable code: default dry-run, explicit per-order user approval, maximum order size, duplicate-position checks, and enforcement of the documented risk rules before any POST or DELETE order request.

ConcernHigh Confidence

ASI04: Agentic Supply Chain Vulnerabilities

What this means

Users may believe order-execution safety checks are included, when the reviewed files only show a lower-level API client with raw order methods.

Why it was flagged

SKILL.md advertises trade and portfolio scripts, including safety checks, but the provided file manifest only includes scripts/kalshi-auth.js and scripts/scan-edges.js. The claimed safety wrapper is therefore not reviewable in the supplied artifacts.

Skill content

- `scripts/trade.js` — Place/cancel orders with safety checks
- `scripts/portfolio.js` — Check balance, positions, P&L

Recommendation

Include the referenced scripts in the package or remove those instructions; make any safety checks visible and enforce them in the reviewed code.