Security audit

Long Article Illustration - 长文配图助手

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent markdown-only assistant for turning long articles into illustration prompts and optional generated images.

Install this as a writing and illustration workflow aid, not as an autonomous publishing tool. Be mindful that article content or prompt details may be shared with whatever image-generation service you choose, and avoid using sensitive unpublished material with third-party tools unless that is acceptable.

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 (5)

Natural-Language Policy Violations

Medium

Confidence: 92% confidence
Finding: The Chinese description states the skill is for automatically generating illustrations for long articles, and the document presents a Chinese-first workflow and output context without any note that users may choose another language. Because language/locale policy violations apply to natural-language instructions in markdown, this reads as a skill oriented to a specific language/locale without explicit opt-in or justification.

Vague Triggers

Medium

Confidence: 93% confidence
Finding: The skill description advertises triggering on broad, common phrases like “文章配图”, “长文插画”, and “段落配图” without clear scoping or stronger contextual constraints. This can cause overbroad activation in unrelated conversations, leading the agent to process user content or invoke image-generation workflows when the user did not explicitly intend to use this skill.

Natural-Language Policy Violations

Low

Confidence: 89% confidence
Finding: This markdown file contains user-facing guidance exclusively in Chinese and does not mention any language-selection option or justification for requiring that locale. Under the policy rule for natural-language violations, forcing a specific language without opt-in can be a locale-policy issue.

Natural-Language Policy Violations

Low

Confidence: 87% confidence
Finding: SQP-3 applies to all file types and covers language or locale policy violations. This markdown file presents all instructions and examples exclusively in Chinese, with no opt-in, alternative language, or justification for a Chinese-only constraint.

Natural-Language Policy Violations

Low

Confidence: 94% confidence
Finding: The troubleshooting guide is written entirely in Chinese and does not indicate that users may choose another language or locale. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy concern.

Static analysis

No suspicious patterns detected.