Security audit

Schedule

Security checks for vulnerabilities and agentic risk

Overview

This scheduling skill is not clearly malicious, but it combines broad automation authority with vague triggers and inconsistent documentation.

Review this skill before installing. Use it only if you are comfortable with an agent potentially reading and writing files, calling APIs, running commands, and creating recurring actions. Require explicit confirmation for every scheduled job, avoid destructive commands or sensitive data, and make sure there is a way to list, stop, and audit any tasks it creates.

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
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (6)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The activation guidance is broad enough to match ordinary project-management or planning conversations, which can cause the skill to be invoked outside the user's intended scope. Because the skill advertises exec, write, and API-related capabilities, overbroad triggering increases the chance of unintended side effects such as task creation, command execution, or external actions based on casual discussion.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 87% confidence
Finding: The description explicitly says the skill supports Chinese interaction and presents the skill primarily in Chinese, but it does not state that users may choose another language. This can amount to a language-policy issue when a skill appears to assume a specific language without opt-in or a documented locale-specific constraint.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The surrounding documentation describes this skill as creating recurring or one-time task schedules, with examples like cron expressions, timer settings, and task status updates. However, the JSON example shows an 'overall_grade', 'total_score', and scoring details, which is a different evaluator-style output and contradicts the claimed scheduling behavior.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 98% confidence
Finding: Earlier documentation states '不适用于：需要分布式任务调度的企业级工作流引擎' and the premium matrix marks distributed scheduling/load balancing as unavailable in the free version. The FAQ then states the scheduling skill supports distributed task scheduling and load balancing, which directly conflicts with those prior limitations.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The skill discloses capabilities for file handling, API integration, and command execution, but it does not present a prominent upfront warning or consent model describing the impact of those operations. In the context of a scheduling skill, this is more dangerous because scheduled or recurring actions can repeatedly perform sensitive operations, amplifying harm from a single mistaken or maliciously crafted request.
Content: No source excerpt is available for this finding.

Vague Triggers

Low

Category: Not specified by scanner
Confidence: 84% confidence
Finding: The invocation guidance is ambiguous and does not define when the skill should engage versus when it should merely answer informational questions. In a skill with operational capabilities, ambiguous triggers can lead to unintended activation and actions without sufficient user intent validation.
Content: No source excerpt is available for this finding.