ClawHub
Back to skill

Security audit

Trip Discover

Security checks for vulnerabilities and agentic risk

Overview

This is a simple travel-recommendation skill whose web and memory use fit its stated purpose, with some privacy guidance around saved places.

Before installing, understand that this skill is meant to use web search for current destination and weather details, and may use saved travel places or known origin city from memory. Avoid using it with saved-place memory if you do not want travel preferences considered in 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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The activation conditions are broad enough to trigger on ordinary travel-related conversation, which can cause the skill to run when the user did not clearly request destination recommendations. In context, that increases the chance of unintended web access or memory use and can lead to confusing or privacy-impacting behavior even without malicious intent.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill instructs the agent to search the web and inspect saved destinations in memory without requiring transparent disclosure or consent at the moment of use. In a travel-planning context, saved places can reveal personal preferences and future plans, so silent access to memory or external lookups creates avoidable privacy and trust risks.

Static analysis

No suspicious patterns detected.