Security audit

PPT 生成器 AI Pro

Security checks for vulnerabilities and agentic risk

Overview

This is a simple presentation-generation skill with broad but coherent routing language and no executable, persistence, credential, or data-exfiltration behavior.

Before installing, note that the skill may activate for broad presentation-related requests and that its pricing/contact sections appear to be artifact text rather than platform billing. Specify your desired language, format, slide count, and export target when using it.

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

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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 (3)

Vague Triggers

Medium

Confidence: 94% confidence
Finding: The skill description is broad enough to match many ordinary requests about presentations, reports, product launches, or pitches, which can cause the agent to invoke this skill when the user only wanted general help rather than a specialized PPT-generation workflow. Over-broad triggering increases the chance of unintended routing, unnecessary capability use, and reduced user control over how their request is handled.

Natural-Language Policy Violations

Low

Confidence: 81% confidence
Finding: L023 明确写有“支持中文排版”，而全文未说明是否支持其他语言或允许用户自行选择输出语言。若技能在使用说明层面默认面向单一语言而未提供用户选择，可能构成语言/locale 策略上的不当限定。

Vague Triggers

Low

Confidence: 87% confidence
Finding: The manifest description says the skill can '一键生成' a Jobs-style PPT, but it does not specify how or when the skill should be invoked, nor any boundaries on supported inputs. In a manifest file, this kind of broad capability description can contribute to ambiguous activation if used for routing or discovery.

Static analysis

No suspicious patterns detected.