Back to skill

Security audit

技能名称生成器

Security checks for vulnerabilities and agentic risk

Overview

This skill only provides naming guidance for OpenClaw skills and does not request code execution, credentials, network access, persistence, or other sensitive authority.

Installers should expect this skill to influence naming responses, especially by producing both Chinese and English options and favoring platform keywords for searchability. Review or narrow the trigger wording if you only want it used for explicit Skill-naming requests.

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
Vulnerability Patterns
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger conditions include very generic phrases like '帮我起个名字', which can overlap with ordinary conversation and cause the skill to activate outside its intended scope. Over-broad activation can hijack user intent, leading the agent to provide naming output when the user wanted broader brainstorming or unrelated help.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill forces bilingual Chinese-and-English output without checking the user's language preference. This can reduce usability, leak unnecessary information into constrained contexts, or create prompt/format conflicts when the caller expects a single-language or minimal response.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

This markdown file contains a natural-language rule that forces a specific language choice for naming: platform names must be incorporated into the English name and mapped to English platform keywords. Under the stated policy, forcing a specific language without user opt-in is a language/locale policy violation.

Content

No source excerpt is available for this finding.