ClawHub
Back to skill

Security audit

Agent Einstein

Security checks for vulnerabilities and agentic risk

Overview

The skill’s disclosed market-research queries and optional paid analysis fit its purpose, with no instructions to collect secrets or execute trades.

Queries and addresses you submit go to emc2ai.io. Check the live tool catalog and prices before authorizing paid use, never share private keys, and treat forecasts as uncertain research.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 9)May include surrounding context.

md
openclaw:
    requires:
      bins:
        - curl
    homepage: https://emc2ai.io/mcp
---

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 55)May include surrounding context.

md
22 deeper tools (token security analysis, wallet analysis, backtests, trade signals, and
others) cost $0.05-$2.00 per call from a prepaid credit balance, or x402 USDC on Base.
Top up at https://emc2ai.io. A paid call without credit returns the payment instructions
instead of data; tell the user rather than retrying. Never ask the user for a private key.

## Rules for answering

Static analysis

No suspicious patterns detected.