ClawHub
Back to skill

Security audit

网红骑行

Security checks for vulnerabilities and agentic risk

Overview

This is a simple cycling-route guidance skill with no executable code, persistence, credential use, or hidden high-impact behavior.

This skill appears safe to install for cycling-route discovery and check-in planning. Users should still verify real-world details such as weather, permits, closures, crowding, and route safety before relying on its recommendations.

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
88% confidence
Finding

The invocation description says the skill should be called when users search for '网红骑行' or plan related travel, which is broader than the skill's narrowly stated purpose of recommending cycling routes and check-in guides. This can cause the orchestrator to route general trip-planning queries to this skill, leading to scope overreach, irrelevant recommendations, or unsafe advice if non-cycling travel needs are handled by a cycling-focused skill.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.