ClawHub
Back to skill

Security audit

网红酒吧

Security checks for vulnerabilities and agentic risk

Overview

This is a simple bar-recommendation guidance skill with no code, installation steps, credential use, persistence, or hidden behavior.

Before installing, expect this skill to influence nightlife or bar recommendation requests. Its recommendations may need current verification for hours, pricing, reservations, and venue rules, but the artifact itself does not add privileged or persistent behavior.

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
91% confidence
Finding

The skill description activates on users searching for网红酒吧 or planning related travel, which is a broad trigger that can match many ordinary nightlife, dining, and trip-planning requests. Overbroad activation can cause this skill to be invoked when users did not intend it, leading to irrelevant guidance, routing of queries away from better-scoped skills, or increased exposure to unvetted recommendations.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.