ClawHub
Back to skill

Security audit

shopping-memory

Security checks for vulnerabilities and agentic risk

Overview

This skill sends shopping notes and purchase history to a BlueColumn/Supabase API for remote memory, which matches its stated purpose but deserves privacy awareness.

Install this only if you are comfortable sending shopping lists, purchase history, store names, prices, and restock notes to BlueColumn/Supabase-hosted services. Avoid recording sensitive business or household details unless you understand the provider's retention and deletion policies.

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
93% confidence
Finding

The skill explicitly instructs agents to send shopping lists, purchase history, store names, prices, and restock timing to a third-party remote API, but provides no privacy notice, consent guidance, retention details, or data-handling limitations. This creates a real privacy and data-governance risk because household or business purchasing patterns can reveal sensitive personal or operational information when transmitted off-platform.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
85% confidence
Finding

This example performs an authenticated POST to an external endpoint and includes detailed shopping history in the request body. The transmission itself is expected for the skill's functionality, but it is still a true security/privacy concern because the documentation normalizes exporting potentially sensitive behavioral data to a remote service without warning, scoping, or safeguards.

Content

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

Capture items the moment they run out or come up.

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": "SHOPPING: need printer ink (HP 63), coffee beans (light roast), dishwasher pods. Ink last bought Jul 1 at Staples, $42.", "title": "shopping - household run"}'

Static analysis

No suspicious patterns detected.