Back to skill

Security audit

雀影

Security checks for vulnerabilities and agentic risk

Overview

This skill is a Chinese-language video storyboard and Seedance prompt-writing assistant with no executable code, hidden persistence, or credential-handling behavior found.

Installers should expect a Chinese-first workflow that may create or edit local storyboard/prompt documents and may tell users how to upload chosen media to external video tools such as 即梦. Review any generated prompts before use and only upload media or voices you have rights and consent to use.

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 (4)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill name, description, keywords, summary, and strategy all assume Chinese as the operating language. This can violate the language/locale policy criterion because the file does not offer user opt-in, alternatives, or indicate that the skill is intentionally limited to Chinese users.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The markdown explicitly requires that all prompts be written in Chinese and repeats the same requirement for image-generation prompts. This imposes a fixed language choice on the user without offering an alternative or opt-in, which matches the language/locale policy violation criteria.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The template requires English view descriptors such as "front view", "side view", and "back view" inside an otherwise Chinese-language skill. This imposes a specific language format without offering user opt-in or explaining that the target tool requires English prompt syntax.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

This markdown file is predominantly written in simplified Chinese, but L191-L206 switches to traditional Chinese for core instructions. Because the file does not explain the language shift or offer a user language/locale option, it can be read as imposing a specific locale variant without opt-in.

Content

No source excerpt is available for this finding.