Security audit

文章配图设计师

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent article-illustration helper with expected image-generation and file-output behavior, and I found no hidden execution, credential access, persistence, or destructive behavior.

Install this if you want a Chinese-oriented article illustration workflow. Be aware it can process article content through ImageGen and save generated images or prompt archives locally; review prompts first when the article contains sensitive or private material.

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

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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

Findings (7)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill description includes broad trigger phrases such as '流程图', '架构图', '关系图', and 'illustrate my article', which can match many unrelated user requests and cause unintended invocation. Over-broad activation can route user content into an image-generation workflow unexpectedly, leading to unnecessary tool use, unintended file creation, or processing of sensitive article text without clear user intent.
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 mandates Chinese handwritten labels and Chinese output conventions by default, without checking the user's language or target audience. This can produce unusable or misleading outputs for non-Chinese users, and in technical diagrams it may also distort labels or force unexpected language transformation of user content, creating integrity and safety issues in the delivered artifact.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: This markdown file contains user-facing instructional content exclusively in Chinese, with no indication that the user can opt into another language or that the skill is intended only for a Chinese-speaking context. That can violate the language/locale policy when a skill effectively forces a specific language without user choice.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The file hard-requires handwritten Chinese labels for every diagram without indicating any fallback based on the user's language or the source article language. In a multilingual illustration skill, this can cause unauthorized language transformation, reduce usability, and produce outputs that do not match user expectations or accessibility needs.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The template hard-codes handwritten Chinese labels and provides a Chinese-only baseline for some models without indicating that language choice should follow user preference or task requirements. This can cause unintended language insertion into outputs, reducing usability, creating misleading or inaccessible diagrams for non-Chinese readers, and potentially causing downstream policy or product-localization violations.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The entire skill guidance is written as mandatory instructions in Chinese, with no indication that users may choose another language or that the skill is intended only for a Chinese-language context. Under the policy, forcing a specific language without opt-in is a natural-language locale violation.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The markdown instructs that if ImageGen is unavailable, the skill should write complete bilingual prompts into files. This is a file-writing behavior that affects the user workspace, but the skill description does not explicitly warn users that files may be created as part of fallback behavior.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.