Security audit

AI图片压缩 | 批量压缩 | 减小体积 | 优化加载 | 青虎AI

Security checks for vulnerabilities and agentic risk

Overview

This is a small, disclosed image-compression skill that uses local ImageMagick commands and does not show hidden data access, persistence, or exfiltration behavior.

Before installing, confirm you are comfortable with the agent using local ImageMagick commands and, if ImageMagick is missing, approving a package-manager install. For bulk jobs, check the input folder and output path so only intended images are processed.

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 (2)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill description says image compression 'must trigger' for broad, common user requests such as compressing images or reducing file size. This can cause the agent to over-invoke the skill in situations where the user did not explicitly ask to use this tool, reducing user control and potentially routing files into an unnecessary processing workflow.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The skill content is written to enforce Chinese-language behavior without indicating that response language should follow the user's preference. This can lead to mismatched-language tool use or outputs, degrading usability and increasing the chance the user misunderstands actions or results, especially when handling file-processing tasks.
Content: No source excerpt is available for this finding.