Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md scripts/resolve.sh "서울특별시 종로구 세종대로 209"
Security audit
Juso Address Cli
Security checks for vulnerabilities and agentic risk
Overview
This skill is a straightforward Korean address lookup CLI that uses disclosed API keys to query the official juso.go.kr service.
Before installing, understand that address searches and your juso.go.kr confirmation key are sent to the official juso.go.kr API. Keep the key in environment variables, avoid passing sensitive personal address data unless needed, and prefer running only the included scripts against the documented juso.go.kr endpoints.
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
Vulnerability Patterns
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md scripts/resolve.sh "서울특별시 종로구 세종대로 209"
Undeclared Tool Scope
Medium
- Category
- MCP Least Privilege
- Confidence
- 91% confidence
- Finding
The skill exposes shell-based execution paths (
scripts/*.sh) but does not declare any explicit tool scope such asallowed-toolsorpermissions. In an agent environment, that ambiguity can cause the skill to be invoked with broader shell access than intended, increasing the risk of command execution, unintended network access, or unsafe handling of user-controlled input through the wrapper scripts.- Content
Missing User Warnings
Low
- Category
- Not specified by scanner
- Confidence
- 82% confidence
- Finding
This code file reads a sensitive environment variable via parameter expansion, but the only disclosure is an internal header comment describing required env vars. There is no user-facing warning, prompt, or runtime notice that the script depends on credential material, which fits the missing-warning criterion for code files accessing sensitive credentials.
- Content