Back to skill

Security audit

学术汇报 PPT 生成技能 (Academic PPT Builder)

Security checks for vulnerabilities and agentic risk

Overview

This skill is a plain Markdown guide for creating academic presentation outlines and does not request tools, credentials, persistence, or privileged access.

Reasonable to install if you want Chinese academic presentation help. Be aware it may trigger on broad PPT requests, so specify the desired context and language when asking for non-academic or non-Chinese slide work.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger list includes a generic phrase such as “生成 PPT,” which is broad enough to match many benign requests unrelated to this specialized academic skill. That can cause unintended invocation, routing users into this skill when they did not ask for academic-presentation assistance, increasing the chance of wrong-context outputs or accidental processing of unrelated pasted content.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill prescribes Chinese-language labeling conventions (for example, axis labels in Chinese + units) and bilingual/English figure elements without checking the user's preferred language. This can cause unintended language coercion, reducing usability and potentially exposing sensitive workflow assumptions when the surrounding session or source materials are in another language.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.