ClawHub
Back to skill

Security audit

ceae-skill

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed hardware root-cause analysis workflow with a local PNG export helper, and I did not find hidden or destructive behavior.

Before installing, understand that engineering conclusions come from the agent following this workflow and should be checked by qualified engineers. If you enable the optional Zhihuiya/PatSnap MCP service, review that service’s account authorization and data scopes separately.

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
80% confidence
Finding
The skill documentation references file-backed/script-backed behavior, including a local export script path, but does not declare corresponding permissions. Undeclared file access can bypass user and platform expectations, increasing the risk of unauthorized local file reads or capability creep if the runtime infers or allows these operations.

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding
This skill claims to perform expert root-cause analysis, collaborative reasoning, Mermaid generation, and PNG export, but the detected behavior reportedly only validates prestructured input and does not implement the promised analysis. That mismatch is dangerous because users may trust the output as if it were independently reasoned engineering analysis, enabling silent failure, incorrect decisions, or unsafe hardware debugging workflows.

Vague Triggers

Medium
Confidence
76% confidence
Finding
Overly broad trigger words can cause the skill to activate in unrelated conversations, leading to accidental invocation of its analysis flow or associated tooling. In a skill that references script execution and engineering outputs, unnecessary activation expands the attack surface and can confuse users into sharing sensitive technical data with the wrong workflow.

Static analysis

No suspicious patterns detected.