ClawHub
Back to skill

Security audit

travel-memory

Security checks for vulnerabilities and agentic risk

Overview

This travel-memory skill openly stores and recalls travel details through a BlueColumn/Supabase API, but users should treat that travel history as sensitive.

Install only if you are comfortable sending travel plans, lodging details, preferences, and trip history to BlueColumn/Supabase-hosted infrastructure. Avoid storing unnecessary identifiers or exact details unless needed, and check the provider's privacy, retention, and deletion practices.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly instructs sending detailed travel itineraries, booking status, preferences, and trip history to remote endpoints, but provides no privacy notice, consent guidance, retention limits, or data-minimization advice. Because travel history and preferences can reveal sensitive behavioral patterns and future absences from home, this creates a real privacy and data-handling risk even if the service is otherwise legitimate.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
91% confidence
Finding

This example performs an authenticated POST to an external service and includes rich travel-memory content in the request body. In the context of a memory skill, external transmission is expected, but it is still security-relevant because it normalizes exfiltration of sensitive personal data to a third-party endpoint without clarifying trust boundaries, consent, or data classification.

Content

Scanner excerpt · SKILL.md (reported line 15)May include surrounding context.

Store the itinerary and the choices that matter for rebooking.

bash
curl -X POST https://xkjkwqbfvkswwdmbtndo.supabase.co/functions/v1/agent-remember \
  -H "Authorization: Bearer $BLUECOLUMN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"text": "TRIP: Lisbon Oct 12-19. Stay: Alfama, airbnb (booked). Flight: TAP outbound 6:40am (hate early — note for next time). Must-do: Sintra day trip, Time Out Market dinner.", "title": "trip - Lisbon Oct"}'

Static analysis

No suspicious patterns detected.