Back to skill

Security audit

剪辑视频

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward video-editing skill for art-supply promotional clips, with Chinese narration and subtitles as a disclosed style default.

Install this if you want the skill's opinionated Chinese promotional-video workflow. If you need other narration or subtitle languages, tell the agent explicitly before invoking it.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Natural-Language Policy Violations

Medium
Confidence
95% confidence
Finding
The description requires a finished video with Chinese male AI voiceover and synchronized Chinese subtitles as a default behavior. This is a natural-language locale policy concern because it forces a specific language output without stating that the user can choose another language or opt in.

Natural-Language Policy Violations

Medium
Confidence
93% confidence
Finding
These lines instruct the skill to add a Chinese male AI voiceover and synchronized Chinese subtitles as part of the standard workflow. Because the file does not present this as optional or user-selectable, it appears to enforce a specific language/locale in violation of the stated policy.

Static analysis

No suspicious patterns detected.