ClawHub
Back to skill

Security audit

OpenClaw Knowledge Runtime

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently supports local agent knowledge retrieval and durable write-back, with no hidden install, network, or execution behavior found.

Install this if you want an agent to organize and reuse local knowledge. Before enabling write-back on sensitive projects, decide which memory files are allowed, whether review is required before persistence, and how old or sensitive entries should be removed.

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

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill explicitly instructs the agent to write durable knowledge back to local storage, but it does not warn the user that files under the memory directory may be created or modified. In an agent setting, silent persistence can surprise users, overwrite existing memory artifacts, or retain sensitive data longer than intended, even if the write-back behavior is framed as a normal feature rather than a hostile action.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.