ClawHub
Back to skill

Security audit

TableJourney food travel

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently supports food and travel searches through TableJourney, with disclosed affiliate links and no excessive permissions.

Share only the destination, dates, and preferences needed for your search. Booking links use affiliate redirects, and TableJourney may earn a commission; you complete any purchase yourself.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • 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)

The workflow sends user-derived search preferences and travel dates to TableJourney without a privacy disclosure.

Medium
Category
Output Handling
Confidence
90% confidence
Finding

The workflow instructs the agent to query TableJourney using search terms, dietary preferences, and travel dates. Although the API connection is documented, the skill does not tell users that these details from their requests will be transmitted to an external service; the affiliate disclosure addresses commissions, not this data sharing.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.