Back to skill

Security audit

Workload Scheduler

Security checks for vulnerabilities and agentic risk

Overview

This skill appears to be a straightforward workload scheduling helper that reads local JSON capacity/template files and prints a schedule, with no evidence of hidden execution, persistence, exfiltration, or destructive behavior.

Before installing, confirm that reading JSON templates from /etc/compute/templates and a capacity report file is appropriate for your environment. Users who do not read Chinese may want translated documentation, and administrators should keep the template directory limited to non-sensitive scheduling specs.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
87% confidence
Finding

The skill documentation indicates it reads workload templates from a template directory, which implies file-read capability, but it does not declare any tool scope such as permissions or allowed-tools. Missing capability scoping weakens least-privilege controls and can allow the runtime or callers to grant broader file access than intended, increasing the chance of unauthorized filesystem reads if the implementation is permissive.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The natural-language content of the skill from the title onward is presented only in Chinese, while the surrounding metadata and audit context do not indicate that this is a region-specific or Chinese-only skill. This can violate language/locale policy because it forces a specific language on users without opt-in or an explicit justification.

Content

No source excerpt is available for this finding.