Back to skill

Security audit

Windows Gateway Sentinel — OpenClaw 常驻运维套件

Security checks for vulnerabilities and agentic risk

Overview

This watchdog can keep OpenClaw running, but it clears safety-related settings and can forcibly stop unrelated services.

Before enabling autostart, preserve deletion safeguards, restrict forced shutdowns to verified gateway processes, and correct custom directory and port handling. Removing the Startup entry is necessary to prevent launch at future logins.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/gateway-daemon.cmd
Finding

Watchdog force-kills listeners without verifying they belong to the gateway

Content
View full analysis

Impact

Forced termination and availability loss for unrelated services accessible to the watchdog account. The cleanup repeats after subsequent gateway exits. No executable identity, gateway ownership, or confirmation check limits the operation.

Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (2)

Unbounded Resource Access

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill allows unbounded resource consumption (API calls, storage, compute). Without rate limits or quotas, a compromised or misbehaving agent can cause denial-of-service or cost overruns.

Content

Scanner excerpt · SKILL.md (reported line 58)May include surrounding context.

md
A normal boot takes **2-3 minutes** (agent-DB integrity gates, six worker
threads, plugin init). The HTTP server logs "http server listening (...; Ns)"
with N typically 120-180. Do not kill and retry at 60s — you will loop
forever, and a second instance will refuse with
"Another gateway (pid N) already owns this state directory".

Frames removal of host-provided deletion safeguards as routine environment cleanup.

Medium
Category
Prompt Injection
Confidence
93% confidence
Finding

The skill explicitly recommends stripping CODEBUDDY_SAFE_DELETE_* and GENIE_TRASH_DIR environment variables, which can disable host-provided safe-deletion or trash-routing protections in the gateway and its descendants. Presenting this as routine cleanup without verifying the protections' purpose or obtaining approval is dangerous, particularly for a persistent, unattended process; the referenced scripts were not supplied, so their actual behavior cannot be verified.

Content

No source excerpt is available for this finding.