ClawHub
Back to skill

Security audit

Openclaw Update

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward OpenClaw update helper, but users should treat its global update and gateway restart commands as impactful maintenance actions.

Install only if you want an agent-accessible reference for updating OpenClaw. Before running the update or restart commands, confirm the package source and target machine, expect the gateway restart to interrupt service briefly, and keep a rollback path available.

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
  • Rogue AgentSelf-Modification, Session Persistence
  • 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 (6)

Self-Modification

High
Category
Rogue Agent
Confidence
85% confidence
Finding

Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.

Content

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

md
"id": "openclaw-update-skill",
              "kind": "skill",
              "path": "skills/openclaw-update",
              "label": "OpenClaw Update Skill",
            },
          ],
      },

Self-Modification

High
Category
Rogue Agent
Confidence
85% confidence
Finding

Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.

Content

Scanner excerpt · SKILL.md (reported line 22)May include surrounding context.

md
"id": "openclaw-update-skill",
              "kind": "skill",
              "path": "skills/openclaw-update",
              "label": "OpenClaw Update Skill",
            },
          ],
      },

Self-Modification

High
Category
Rogue Agent
Confidence
85% confidence
Finding

Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.

Content

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

md
"id": "openclaw-update-skill",
              "kind": "skill",
              "path": "skills/openclaw-update",
              "label": "OpenClaw Update Skill",
            },
          ],
      },

Self-Modification

High
Category
Rogue Agent
Confidence
85% confidence
Finding

Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.

Content

Scanner excerpt · skills/SKILL.md (reported line 22)May include surrounding context.

md
"id": "openclaw-update-skill",
              "kind": "skill",
              "path": "skills/openclaw-update",
              "label": "OpenClaw Update Skill",
            },
          ],
      },

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

This markdown file instructs users to run global package upgrade commands and restart the OpenClaw gateway, which can modify the installed software state and interrupt service. The description presents these actions as routine workflow steps but does not include a clear warning about their impact, risks, or the need to ensure the user intends to change the installation.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill includes commands that globally update the OpenClaw package and restart the gateway, both of which modify the system state and can interrupt service. Because the documentation presents these actions as routine workflow steps without an explicit warning, confirmation requirement, or rollback/safety guidance, an agent or user could apply disruptive changes too casually.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.