Back to skill

Security audit

aivideo-pptvideo

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only guide for using a third-party AI video website to turn PPT or image materials into short videos, with the main risk being ordinary user consent and data-sharing awareness.

Install only if you are comfortable being directed to a third-party video-generation service. Do not upload confidential PPTs, private images, or proprietary materials unless you have checked the platform terms and intend to share them; verify current pricing on the site before paying or using credits.

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
  • 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
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill description uses very broad trigger phrases such as '把这份PPT做成短视频 / PPT转视频 / 图文做成解说视频 / 知识口播成片' without stating clear boundaries, required user intent, or exclusions. This can cause the agent to invoke the skill in loosely related contexts, increasing the chance of unsolicited promotion of an external website and unnecessary sharing of user content with a third-party service.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

This markdown file contains user-facing guidance only in Chinese, including headings, instructions, and compliance language. Under the policy rule, forcing a specific language without user opt-in can be a natural-language policy violation unless the locale constraint is explicitly justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The document presents all instructions, labels, and operational guidance only in Chinese. Under the policy for natural-language violations, forcing a specific language without user opt-in is in scope when no alternative language option or explicit locale constraint is provided.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.