Security audit

LH DeepWiki

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small DeepWiki client that sends user-supplied public GitHub repository questions or paths to DeepWiki and does not show hidden persistence, credential access, or destructive behavior.

Before installing, users should be comfortable with repository names and questions being sent to DeepWiki's external MCP service. The skill is documented primarily in Chinese, so non-Chinese-speaking users may need translation to fully understand the usage notes.

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: 96% confidence
Finding: The natural-language content of the skill instructions and usage guidance is presented in Chinese, but the file does not indicate that the skill is region-specific or offer users an alternative language. This can violate language/locale policy expectations when users are not given opt-in or choice.
Content: No source excerpt is available for this finding.