ClawHub
Back to skill

Security audit

automation-workflow-builder（自动化工作流构建器，设计并执行跨平台自动化流程，支持定时触发、文件监控、多步骤操作。适用于数据同步、内容发布、报告生成。）

Security checks for vulnerabilities and agentic risk

Overview

This automation skill is not deceptive, but it asks for broad command, file, and network authority without enough scoping or user-control guidance.

Review this skill carefully before installing. It is intended to automate powerful tasks, so only use it with explicit approvals for command execution, uploads, publishing, file moves/deletes, and scheduled or file-watching workflows. Prefer narrow working directories, known network destinations, and workflows that can be stopped or audited.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (8)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill advertises file operations, network requests, command execution, and notifications as supported workflow actions, but provides no safety guidance about side effects, permissions, data exfiltration, or destructive behavior. In an automation skill, these capabilities materially increase risk because users may run workflows that modify local state, execute arbitrary commands, or send data externally without understanding the impact.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The examples normalize potentially sensitive actions such as fetching external data, saving locally, watching directories, moving files, uploading to cloud storage, and publishing content without any warning or constraint model. Because these are concrete usage patterns, they can encourage unsafe deployment and make accidental data leakage, unauthorized publishing, or filesystem damage more likely in real environments.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 51)May include surrounding context.

md
const workflow = {
  trigger: { type: "cron", schedule: "0 */6 * * *" },
  steps: [
    { action: "fetch", url: "https://api.example.com/data" },
    { action: "transform", script: "process(data)" },
    { action: "save", path: "./output/data.json" }
  ]

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
79% confidence
Finding

The natural-language description is presented only in Chinese, which can indicate a language-specific constraint without any visible opt-in, multilingual alternative, or documented regional justification. Under the locale policy, a skill should not implicitly force a specific language unless the limitation is clearly offered as a choice or justified as region-specific.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger list contains broad, generic terms such as 'automation', 'workflow', 'cron', and their Chinese equivalents, which are likely to match many ordinary user requests outside the intended scope. Because this skill also declares powerful capabilities including exec, read, write, and web_fetch, accidental invocation could route benign requests into a high-privilege automation tool and increase the chance of unsafe actions being proposed or executed.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The changelog is entirely written in Chinese, including headings and feature descriptions, with no indication that users can choose another language or that the locale restriction is intentional. This can violate language/locale policy where skills should not force a specific language without user opt-in or documented justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The natural-language content of the skill forces a specific language presentation for the description and instructions, with no indication that users can choose another language or that the skill is intentionally region-specific. This matches the language/locale policy concern for skills that impose a language without user opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The skill's visible name and summary are entirely in Chinese, but the metadata does not state that the skill is region-specific or that users can opt into a preferred language. Under the language/locale policy, this can be a natural-language policy concern because it implicitly fixes the skill's user-facing language.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.