ClawHub
Back to skill

Security audit

memory-audit

Security checks for vulnerabilities and agentic risk

Overview

This is a read-only memory-audit skill that scans local OpenClaw memory files and reports manual cleanup suggestions without editing files or contacting external services.

Install only if you are comfortable letting the skill read your OpenClaw memory and related bootstrap files to produce a local report. Review suggested edits manually; the skill is designed not to apply changes itself.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding

The skill invokes local code and reads from an agent workspace, but it does not declare an explicit tool scope such as permissions or allowed-tools. That mismatch can cause the runtime or reviewer to underestimate the skill's effective file access, increasing the chance of unintended data exposure if the skill is enabled in a broader environment.

Content

No source excerpt is available for this finding.