ClawHub
Back to skill

Security audit

雀影

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent Chinese-language video/storyboard prompt-writing skill with no evidence of hidden execution, persistence, credential access, or exfiltration.

Install if you want a Chinese-language assistant for Seedance/AI-video storyboards. Be aware that its generic video-related triggers may activate often, and only provide or upload reference media you intend to use with the video/image tools or external platforms.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (11)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The trigger list contains broad, generic phrases such as '视频生成', 'AI视频', '分镜', and '字幕' that are likely to match many ordinary user requests outside the narrow intended scope of this skill. This can cause the skill to activate too often, unexpectedly steer conversations, and increase the chance that file-writing or editing behaviors are invoked in contexts where the user did not intend to use this specialized workflow.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill hard-requires all prompts to be written in Chinese, without checking or honoring the user's preferred language. This can degrade usability, cause misunderstanding of generated instructions, and create accessibility or inclusion issues for non-Chinese-speaking users, though it is not a direct security exploit.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill mandates Chinese-only image-generation prompts, again without user opt-in or fallback. This may lead to user confusion, reduced prompt effectiveness on some tools, and exclusion of users who need another language, making the workflow less safe and reliable from a product-policy perspective.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

This markdown file prescribes a fixed language-specific output format such as 角色名："台词" and related Chinese labeling rules for all subtitles. Because the policy applies to all file types and disallows forcing a specific language without opt-in, this is a natural-language locale policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The file is entirely framed as a normative writing specification in Chinese and does not indicate that language choice is optional or limited to a clearly justified region-specific use case. Per the policy, forcing a specific language or locale without user opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
83% confidence
Finding

This markdown file is entirely framed as a normative specification in Chinese and does not indicate that language choice is optional or user-selected. Under the stated policy, forcing a specific language or locale without opt-in can be a natural-language policy violation unless the locale constraint is clearly documented and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

This markdown file contains extensive natural-language instructions and dialogue exclusively in Chinese, but nowhere indicates that Chinese output is optional or limited to a justified region-specific use case. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

This markdown file presents all instructions, prompts, and scene descriptions exclusively in Chinese, with no indication that users may choose another language or locale. Under the policy rule for language or locale constraints, forcing a single language without user opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

Line L028 explicitly specifies '在日本县城郊区的工业园中' as the setting, imposing a Japan-specific locale in the prompt text. The file does not offer any user opt-in, alternative locale choice, or justification that this skill is intended only for a Japan-specific use case.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The document instructs users to choose voices based on fixed attributes including '年龄、性别、性格、情绪'. This is a natural-language locale/policy-style constraint on presentation characteristics without any opt-in, alternatives, or justification, which can be interpreted as imposing demographic assumptions rather than offering choice.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
73% confidence
Finding

The line specifies that a side character should '带口音' and '内心独白几乎没有', which imposes a fixed language/presentation choice in natural language rather than offering alternatives. Because the file does not indicate these are optional examples or user-selected preferences, this can conflict with organizational expectations around language/locale choice.

Content

No source excerpt is available for this finding.