ClawHub
Back to skill

Security audit

OpenClaw Ollama Memory

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward local Ollama memory-search setup guide, with a disclosed but user-controlled option to index extra Markdown paths.

Before enabling extraPaths, only add directories you intentionally want OpenClaw memory search to index, especially because absolute paths and recursive Markdown scanning may include private notes or shared documents. The default local Ollama setup otherwise avoids cloud embedding APIs and does not require an API key.

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)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The documentation explicitly permits absolute and workspace-relative extra indexing paths and states that directories are scanned recursively for Markdown files, but it does not warn that this can pull data from outside the intended workspace boundary. In a memory-search skill, that can cause unintended ingestion of sensitive notes, shared documents, or system-adjacent content into the searchable corpus, increasing the risk of data exposure through later queries.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.