Security audit

Visual

Security checks for vulnerabilities and agentic risk

Overview

This is a small text-only visual-design skill with some off-topic collaboration guidance, but it does not request system access or perform actions.

Install only if you are comfortable with a Chinese-language visual-design helper that may also answer collaboration or product-support questions. Treat its permissions, sharing-link, storage, and sync guidance as generic advice rather than a dedicated security or admin skill.

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

Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
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

Findings (5)

Description-Behavior Mismatch

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill advertises visual design guidance, but most of the body describes collaboration modes, permissions, sharing, version history, storage, sync, and project tracking. This scope mismatch can cause the agent to invoke the skill for unrelated operational or access-control queries, expanding behavior beyond user expectations and creating opportunities for inappropriate guidance or data-handling confusion.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The example prompts are broad and generic enough to match ordinary user requests, increasing the likelihood of over-triggering the skill. In combination with the scope drift elsewhere in the document, this can cause the agent to invoke the skill in contexts unrelated to visual design and return irrelevant or unsafe guidance.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 83% confidence
Finding: The natural-language content of the skill is entirely Chinese, and the file does not state that this language requirement is optional, user-selected, or justified by a region-specific purpose. This can create a language policy issue if the organization expects skills not to force a language or locale without user opt-in.
Content: No source excerpt is available for this finding.

Context-Inappropriate Capability

Low

Category: Not specified by scanner
Confidence: 89% confidence
Finding: Introducing permission granularity and sharing-link guidance in a visual-design skill is an unjustified capability expansion into access-control topics. Even if not directly executable, it can mislead routing and encourage the skill to answer security-sensitive questions without a legitimate need or clear safeguards.
Content: No source excerpt is available for this finding.

Context-Inappropriate Capability

Low

Category: Not specified by scanner
Confidence: 88% confidence
Finding: Storage capacity, cloud sync state, and export-format support are operational product-management topics rather than visual-design guidance. This mismatch broadens the skill's apparent domain and can trigger it for unrelated system or data-flow questions, undermining clear trust boundaries.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.