Security audit

Image Scanner

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent image-folder scanner with no evidence of hidden execution, network access, persistence, credential use, or implemented destructive behavior.

Install only if you are comfortable with a Chinese-language image scanning tool. Use it on a specific test folder first, and treat any future classification mode that actually moves files as opt-in bulk file organization requiring review of the report and output path.

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 (4)

Vague Triggers

Medium

Confidence: 93% confidence
Finding: The trigger phrases are broad and action-oriented, which can cause the skill to activate in response to vague user requests such as scanning or organizing photos without clear confirmation boundaries. Because the skill can perform bulk file operations and potentially move files, ambiguous activation increases the risk of unintended execution and accidental modification of user data.

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The documentation states that the skill can automatically create subfolders and move files, but it does not prominently warn users that classification may modify filesystem contents. In a bulk-processing context, this can lead to accidental file relocation, workflow disruption, or apparent data loss if users expect analysis-only behavior.

Natural-Language Policy Violations

Medium

Confidence: 95% confidence
Finding: This code contains user-facing console output and inline operational messaging in Chinese only, such as the scan/report messages and warnings. Because the file does not offer a language selection or explain that the skill is intentionally region-specific, it risks violating a language/locale policy requiring user opt-in or documented justification.

Natural-Language Policy Violations

Low

Confidence: 81% confidence
Finding: All user-facing descriptive text and trigger phrases are presented in Chinese, which can impose a language constraint without opt-in or explanation. Under the policy, a forced language or locale should either provide user choice or clearly document a justified locale-specific scope.

Static analysis

No suspicious patterns detected.