Back to skill

Security audit

更新守护者

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed update-management guide that uses command execution to check, snapshot, update, schedule, and roll back agent skills, with no hidden code or exfiltration behavior found.

Before installing, confirm the update-manager CLI is one you trust, run dry-run checks first, verify snapshots and rollback work, and set the schedule timezone and blackout windows for your own environment rather than accepting the Asia/Shanghai examples unchanged.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The markdown hard-codes tz: "Asia/Shanghai" and repeats scheduling examples in Asia/Shanghai, which is a locale-specific default presented as the normal behavior. Because the skill is described as supporting arbitrary agent platforms and multiple operating systems, this fixed locale is not clearly justified and no user opt-in or alternative locale choice is described here.

Content

No source excerpt is available for this finding.