Security audit

Batch Image Processor Pro

Security checks for vulnerabilities and agentic risk

Overview

This is a simple batch image-processing skill whose file operations are expected for its stated purpose and are disclosed at a high level.

Install only if you are comfortable with a Chinese-language image-processing skill and plan to process copies or use separate output folders until you know whether the implementation overwrites originals or removes metadata such as EXIF data.

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

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (2)

Missing User Warnings

Medium

Confidence: 90% confidence
Finding: The skill advertises destructive or data-altering image operations such as compression, format conversion, renaming, cropping, and EXIF stripping without warning users that files or metadata may be permanently changed or lost. In a batch-processing context, this increases the chance of large-scale accidental data loss, especially if users expect non-destructive behavior or do not realize privacy-relevant metadata will be removed.

Natural-Language Policy Violations

Low

Confidence: 84% confidence
Finding: The file uses Chinese for headings, commands, and descriptions, which may impose a language requirement on users without opt-in. The policy allows locale constraints when clearly documented and justified, but no such justification or alternative language option is provided here.

Static analysis

No suspicious patterns detected.