Back to skill

Security audit

Jiaopei Skill

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only Chinese education-business operations skill, with no code execution or persistence, but users should add privacy safeguards before using its student photo-sharing templates.

Before installing, treat this as business-advice content rather than an automated operator. If used with children's information, revise the templates to require parent or guardian consent, share only through approved private channels, avoid faces/names where unnecessary, and remove identifying details from screenshots or photos.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The description is written to imply Chinese-language operation without checking the user's language preference, which can cause the skill to respond in a language the user did not request. This is primarily a safety and usability issue because it may reduce comprehension, produce mistaken actions, or exclude users who expected another language.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger terms are very broad and cover common education-business topics, which can cause the skill to activate in conversations where the user did not intend to invoke this specialized workflow. Unintended invocation can override more relevant system behavior, steer the conversation into business-operational advice, and increase the chance of inappropriate data collection or context confusion.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The template explicitly instructs staff to send a child's work screenshot or photo but provides no requirement to obtain parental consent, minimize identifying information, or restrict sharing scope. In an education context involving minors, this creates a real privacy risk because images can expose personal data, faces, names, school materials, or metadata and may be shared beyond the intended audience.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The template suggests attaching a class group photo or student photo without any privacy, consent, or audience-limitation guidance. Because this skill is for training institutions serving children and families, normalizing photo sharing without safeguards can lead to unauthorized disclosure of minors' identities and broader circulation of their images.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.