Security audit

단위 변환

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward local unit converter with Korean-language documentation and messages, and it does not show hidden access, persistence, network use, or destructive behavior.

Install this if you are comfortable with a Korean-oriented unit conversion helper that runs a local Python script. It does not require network access or credentials, but non-Korean users may find the documentation and messages less accessible.

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 (3)

Natural-Language Policy Violations

Medium

Confidence: 90% confidence
Finding: The manifest description is entirely in Korean and frames the skill's invocation/examples in Korean-only terms, with no indication that users may interact in other languages or opt into this locale. Under the policy, language or locale constraints should be optional or explicitly justified if region-specific.

Natural-Language Policy Violations

Low

Confidence: 81% confidence
Finding: This JSON file includes many Korean-language aliases alongside English aliases across multiple unit categories, but there is no accompanying metadata or documentation indicating that Korean locale handling is optional, user-selected, or limited to a region-specific context. Under the stated policy, embedding a specific language/locale without opt-in can be considered a natural-language locale policy issue.

Natural-Language Policy Violations

Low

Confidence: 90% confidence
Finding: The file’s user-facing natural language strings, including the module docstring, CLI help text, and error/output messages, are all written in Korean. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is explicitly documented and justified.

Static analysis

No suspicious patterns detected.