Security audit

control-mirror

Security checks for vulnerabilities and agentic risk

Overview

This skill is a documentation-only architecture review aid with no evidence of hidden execution, data access, persistence, or privilege use.

Installers should expect a review framework for architecture stability and agent-system control loops. The only notable caveat is that some examples and one reference file are in Chinese, which may affect usability for non-Chinese readers but does not add security risk.

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 (1)

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: Multiple prompt strings are written as direct Chinese-language instructions, which imposes a specific language/locale on use of the skill artifacts. The file does not offer a language choice or explain a region-specific reason for requiring Chinese, so this is a natural-language policy concern under the locale rule.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.