ClawHub
Back to skill

Security audit

Travel Claw(旅行龙虾)

Security checks for vulnerabilities and agentic risk

Overview

This skill is a creative travel-story generator with limited, disclosed context use and optional image search after consent.

Installers should expect the skill to use the current conversation to infer a nickname and output language, and to ask before using public image search. Ask for a specific language if the automatic choice is not what you want.

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

Low
Confidence
93% confidence
Finding
The description states the skill will use Chinese for Chinese users and English otherwise, which imposes a language choice based on inferred user category rather than offering an explicit preference. The policy allows language constraints only when users are given a choice or the constraint is clearly justified.

Static analysis

No suspicious patterns detected.