ClawHub
Back to skill

Security audit

Heartbeat Tasks

Security checks for vulnerabilities and agentic risk

Overview

This skill openly describes heartbeat automation, but it also directs autonomous crypto trading and memory cleanup without clear approval or rollback controls.

Review carefully before installing. This should only be used in an environment where autonomous crypto trading and memory-file mutation are intended, constrained to known accounts and paths, and protected by separate confirmation, limits, audit logs, and backup controls.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill instructs an agent to perform real-world and data-affecting actions, including executing trades, updating persistent state, modifying memory files, and cleaning or archiving data, but it provides no explicit approval gates, dry-run mode, rollback guidance, or user warning about those side effects. In an autonomous heartbeat context, this is dangerous because recurring execution amplifies mistakes and could cause financial loss or irreversible data modification without immediate human review.

Static analysis

No suspicious patterns detected.