Back to skill

Security audit

Heartbeat Monitor

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple heartbeat-status monitor with disclosed local state tracking and no bundled executable code.

Install this only if you want the agent to keep a persistent heartbeat state file and possibly use scheduling or reminders for stale checks. Review any future implementation before enabling automatic repair or cron behavior.

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
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 (2)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill explicitly advertises 'automatic repair' and documents a writable state file under the user's home directory, but it does not warn that invoking the skill may modify persistent local state or trigger follow-up checks/tasks. In an agent setting, undocumented state changes and automatic task execution can surprise users, create unintended actions, and expand the effect of a simple status check into broader autonomous behavior.

Natural-Language Policy Violations

Low
Confidence
91% confidence
Finding
SQP-3 applies to all file types and covers language or locale policy violations. The natural-language instructions, headings, and usage guidance are presented only in Chinese, which can amount to forcing a specific language absent user opt-in or an explicit region-specific justification.

Static analysis

No suspicious patterns detected.