ClawHub
Back to skill

Security audit

问句需求调研

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed spreadsheet-processing template that reads user-provided BI requirement documents and creates a derived Excel model, with no evidence of hidden execution, persistence, credential use, or data exfiltration.

Install only if you intend the agent to read the uploaded workbook, including auxiliary sheets, and create a derived Excel model from its contents. Review the generated workbook before sharing it, because it may include inferred metrics, dimensions, business rules, and reference information from the source documents.

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 (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill describes ingesting uploaded XLSX files and generating a new Excel workbook, but it does not warn the user that their documents will be transformed and written into a derived file. Without an explicit notice, users may unknowingly expose sensitive spreadsheet contents, embedded reference sheets, or business metadata into a newly generated artifact that could be stored, shared, or overwrite expectations about data handling.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill explicitly claims applicability to arbitrary projects and business domains without narrowing when it should or should not be invoked. In an agent setting, this broad trigger surface can cause the workflow to process unrelated uploaded spreadsheets and synthesize authoritative-looking outputs from insufficient or mismatched context, increasing the chance of unsafe automation and data handling errors.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The entire skill, including its name, description, and operating instructions, is written only in Chinese and does not indicate that users may choose another language or locale. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is explicitly justified.

Content

No source excerpt is available for this finding.