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
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.

Content

Scanner excerpt · SKILL.md (reported line 37)May include surrounding context.

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"}'

Missing User Warnings

Medium
Category
Not specified by scanner
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.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
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.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.