ClawHub
Back to skill

Security audit

Foreseek AI

Security checks for vulnerabilities and agentic risk

Overview

The skill is coherent for prediction-market trading, but it can send sensitive account data to an external endpoint and place or cancel real-money Kalshi orders without a strong confirmation requirement.

Install only if you intend to let an agent access your Foreseek/Kalshi trading workflow. Use a scoped, revocable API key, verify whether the connected account is demo or live before use, and require your own explicit approval for every trade or cancel action.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

External Transmission

Medium
Category
Data Exfiltration
Content
Converts natural language to matched Kalshi contracts.

```bash
curl -X POST https://jxvtetqmzduvhgiyldgp.supabase.co/functions/v1/foreseek-cli \
  -H "Authorization: Bearer $FORESEEK_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"operation": "parse", "prediction": "Fed will cut rates in March"}'
Confidence
80% confidence
Finding
The documented workflow transmits user predictions and an API bearer token to an external Supabase-hosted endpoint. While external API use is expected for this skill, it still creates a real data-exposure and trust-boundary risk because sensitive inputs, authentication credentials, and potentially financial context are sent off-platform to a third-party service.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill explicitly documents a `trade` operation that can execute buy/sell orders on a connected Kalshi account, but the surrounding description does not clearly warn users that this may place real-money orders. In an agent setting, lack of a prominent transactional warning increases the risk of unintended financial actions, especially if users think they are only querying markets or getting informational output.

Missing User Warnings

Low
Confidence
88% confidence
Finding
The skill sends requests, including account-related operations such as positions, orders, balance, watchlist, and status, to an external Foreseek endpoint but does not clearly disclose that portfolio/account data will be shared with a third-party service. This weakens informed consent and can expose sensitive financial metadata, trading activity, and account linkage information to an external processor.

Static analysis

No suspicious patterns detected.