ClawHub
Back to skill

Security audit

Hello World

Security checks for vulnerabilities and agentic risk

Overview

This is a simple hello-world OpenClaw plugin that registers one greeting tool and does not access files, network, credentials, memory, or privileged system features.

This plugin is appropriate for testing a hello-world OpenClaw setup. Be aware that it may respond to ordinary greetings by calling its hello tool, and users who need strict reproducible builds may want dependency versions pinned before production use.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

Vague Triggers

Medium
Confidence
96% confidence
Finding
The manifest description says to use the skill when the user 'asks for a hello, a greeting, says hi,' which are very common conversational phrases and not narrowly scoped to plugin use. This can cause unintended invocation during ordinary chat because the activation boundary is not clearly limited beyond a general greeting.

Vague Triggers

Medium
Confidence
97% confidence
Finding
The instruction to trigger when the user asks for a greeting, says 'hello' or 'hi' is too broad because those phrases commonly occur in normal conversation. The file does not provide negative examples or constraints distinguishing casual greetings from intentional skill invocation.

Unverifiable Dependency: openclaw has 16 known advisory(ies) (CVE-2026-53846 (OpenClaw: Workspace .env npm_execpath could influence bundled runtime dependency); CVE-2026-32064 (OpenClaw's andbox browser noVNC observer lacked VNC authentication); CVE-2026-32006 (OpenClaw has a BlueBubbles group allowlist mismatch via DM pairing-store fallbac) +13 more), but the manifest does not pin a version, so it is unknown whether the installed release is affected

Low
Category
Supply Chain
Confidence
40% confidence
Finding
Dependency has known vulnerabilities (CVEs). Using packages with unpatched security flaws exposes the environment to known exploits.

Unpinned Dependencies

Low
Category
Supply Chain
Content
"openclaw": ">=2026.3.24-beta.2"
  },
  "dependencies": {
    "@sinclair/typebox": "^0.32.0"
  },
  "devDependencies": {
    "typescript": "^5.4.0"
Confidence
40% confidence
Finding
Dependencies lack version pinning, allowing potential malicious package updates. Consider pinning versions.

Unpinned Dependencies

Low
Category
Supply Chain
Content
"@sinclair/typebox": "^0.32.0"
  },
  "devDependencies": {
    "typescript": "^5.4.0"
  }
}
Confidence
40% confidence
Finding
Dependencies lack version pinning, allowing potential malicious package updates. Consider pinning versions.

Static analysis

No suspicious patterns detected.