Security audit

流程架构师

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only workflow design skill whose side-effect capabilities are disclosed and aligned with its automation purpose.

Before using this skill for live automation, review the YAML workflow destinations, affected files, API endpoints, notification channels, credentials, and dry-run results. Prefer manual or dry-run execution first, especially for uploads, writes, notifications, and external API calls.

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 (2)

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The skill declares very broad trigger keywords such as '工作流构建', '自动化流程', '触发器', and '条件分支', which can plausibly appear in ordinary user requests unrelated to this specific skill. Because the skill also exposes read and exec-capable workflow design/execution behavior, accidental activation increases the chance of unintended file operations, external requests, or workflow execution in contexts where the user did not explicitly opt in.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The skill clearly describes capabilities that can perform external HTTP requests, write files, send notifications, and execute workflows, yet it does not present a consolidated user-facing risk notice or consent boundary before operational steps. In a skill with read and exec tools, this omission can lead users to invoke actions with side effects without understanding data exposure, outbound communication, or filesystem modification risks.

Static analysis

No suspicious patterns detected.