ClawHub
Back to skill

Security audit

Workflow Essentials Free

Security checks for vulnerabilities and agentic risk

Overview

This is mostly a plain Chinese guide for learning automation workflows, but it asks for broad shell-command access that is only weakly justified.

Review this before installing if your agent would receive shell-command capability from the skill. The instructional content appears benign, but a safer version would remove `exec` or require explicit user confirmation and a narrow allowlist for diagnostics such as `ping`. Expect to use separate Zapier, Make, or n8n accounts if you follow the workflow-building guidance.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (4)

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill is presented as an introductory workflow guide, but it requests exec capability despite not defining a concrete, necessary command-execution use case. This creates unnecessary privilege exposure: an agent may be permitted to run shell commands in contexts where users expect only instructional content, increasing risk of unintended command execution or abuse if later prompts steer the agent toward system actions.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

For a beginner-oriented guide, declaring exec is inconsistent with the stated functionality and expands the agent's operational surface beyond what users would reasonably expect. Even without explicit malicious instructions in the file, this mismatch can enable risky behavior through prompt injection, user misunderstanding, or accidental execution of diagnostic commands on the host.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The line explicitly states that all content has been fully localized to Chinese and rewritten for Chinese users. Because the skill does not provide an opt-in language choice or clearly justify a mandatory locale restriction elsewhere, this is a natural-language locale policy concern under the stated rules.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
76% confidence
Finding

The API Key section says no extra API key is needed, which suggests minimal setup and self-contained use. Yet the surrounding dependency lines state the skill requires access to external SaaS automation tools and account authentication on those platforms. While not a direct technical contradiction about this skill's own API key, the documentation meaningfully understates the operational dependency and authentication burden.

Content

No source excerpt is available for this finding.