Security audit

Skillhub Preference

Security checks for vulnerabilities and agentic risk

Overview

This is a small policy-only skill that prefers one skill registry before falling back to another, with no bundled code or hidden persistence.

Before installing, understand that this skill changes agent preference for skill-related tasks: it will try skillhub first, then clawhub if needed. Review the source, version, and risk summary before approving any actual skill installation.

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

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The description says to use the skill when users ask about 'skills, 插件, or capability extension,' which is broad and lacks explicit constraints or negative examples. This can overlap with ordinary conversation about capabilities or plugins and may cause unintended invocation outside the intended skill discovery/install/update context.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.