Security audit

Wiki Retriever

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple wiki document retrieval helper, with no executable code, persistence, or hidden behavior found.

Before installing, understand that this skill is intended to inspect wiki and user-uploaded files relevant to a retrieval request. Use it when you want document retrieval, and be cautious in workspaces containing sensitive uploads because the activation description is broad.

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

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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

Findings (1)

Vague Triggers

Medium

Confidence: 92% confidence
Finding: The skill description is overly broad ('AI agent for wiki retriever tasks') and does not define clear activation boundaries, allowed data sources, or user-intent constraints. In an agentic environment, vague routing criteria can cause the skill to activate for loosely related requests and then enumerate or read broad sets of wiki/uploaded files, increasing the chance of unnecessary data exposure or over-collection.

Static analysis

No suspicious patterns detected.