Back to skill

Security audit

Ai Director

Security checks for vulnerabilities and agentic risk

Overview

This is a knowledge-only film directing assistant with disclosed Chinese-heavy references and no hidden automation, persistence, credential access, or destructive behavior.

Install only if you want a Chinese-forward film directing/pre-production helper based on Katz-style shot planning. Users who need fully English templates may need to ask the agent to respond in English, but there is no evidence of hidden code execution or sensitive access.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (12)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The document is written as a Chinese rules reference and usage guide, including instructional sections for an AI director, but it does not indicate that the user may choose another language or that Chinese is required for a region-specific purpose. This can violate language/locale policy where skills should not force a specific language without user opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

This markdown file contains user-facing instructional content in Chinese throughout, including headings, workflow steps, and guidance, but does not indicate that the language is optional or limited to a Chinese-speaking audience. Under the 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

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The file title and surrounding instructional content are primarily in Chinese, and the document presents the skill philosophy in that language without indicating that users may choose another language. This creates a natural-language locale policy concern because the skill appears to enforce a specific language by default rather than offering opt-in or an alternative.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The file presents the skill content primarily in Chinese and does not offer a user-language choice or document a hard locale requirement. In an agent setting, this can cause user intent mismatch, reduce transparency, and lead users to rely on instructions they cannot fully understand, which is a genuine quality and safety issue even though it is not a classic exploit primitive.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill explicitly instructs the agent to respond in Chinese by default, even though activation examples and surrounding content are multilingual. This can override or ignore the user's actual language preference, creating a prompt-quality and user-trust issue and, in some environments, causing unintended disclosure or mishandling if output language affects downstream review or operator comprehension.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

This markdown file is primarily in Chinese, but the title includes an English subtitle, which indicates multilingual presentation without any user opt-in or explanation of the intended language/locale. Under the policy criteria, forcing or assuming a language without offering choice can be a natural-language policy issue unless the locale scope is explicitly documented.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

This markdown file contains user-facing natural language exclusively in Chinese, including the title, section headings, and checklist items. Under the policy criteria, forcing a specific language without user opt-in can be a language/locale policy violation, and this file does not indicate that the Chinese-only format is optional or region-specific.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

This markdown template is entirely written in Chinese, including headings, labels, and checklist items, with no indication that language selection is optional or that the template is intended only for a Chinese-speaking or region-specific workflow. That can violate a language/locale policy when users are not given an opt-in or alternative.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The entire template and usage guidance are written in Chinese, and the file does not indicate that other languages are supported or that Chinese is optional. Under the policy, forcing a specific language without opt-in can be a natural-language policy violation unless the locale constraint is explicitly documented and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The title presents the skill as Chinese-language content ("运动镜头速查") with no indication that users may choose another language or locale. Under the policy rule, forcing a language without opt-in is a natural-language policy concern when no alternative or user choice is offered.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

The title presents the content bilingually but prominently in Chinese, and the document consistently delivers guidance in Chinese throughout without any note that language can be selected by the user. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation unless the locale constraint is documented and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

This markdown reference is written primarily in Chinese, including the title and instructional section, with no indication that users may choose another language or that the skill is intentionally limited to a Chinese-speaking context. Under the policy rule for natural-language violations, forcing a specific language without opt-in can be a locale-policy issue.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.