ClawHub
Back to skill

Security audit

测试用例生成器

Security checks for vulnerabilities and agentic risk

Overview

This is a test-case generation skill with expected export behavior and no evidence of hidden, destructive, network, credential, or persistence activity.

Installers should expect this skill to help produce structured test cases and, if CSV or Excel output is requested, to create local files named testcases.csv or testcases.xlsx. Review generated test data before sharing it, especially if requirements contain confidential product or business details.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (5)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest description says the skill should be used whenever a user needs to write test cases, design test scenarios, generate test points, create a test matrix, or perform coverage analysis, and also lists broad phrases like "测试场景" and "test case". These triggers are expansive and lack exclusion conditions or clear boundaries, which increases the chance of unintended invocation in ordinary discussion about testing.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill goes beyond generating test cases and instructs the agent to generate and execute Python that writes CSV/XLSX files. That introduces code-execution and filesystem-write behavior into a content-generation skill, expanding its privilege and attack surface; if combined with untrusted testcase content or automatic tool use, it could cause unintended local file creation or downstream misuse.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill tells the agent to execute CSV-export code that creates a local file without notifying the user or requiring confirmation. Silent filesystem writes violate user expectations and can be abused to create artifacts from untrusted content or trigger unintended side effects in environments where tool execution is enabled.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The Excel export path similarly directs the agent to run code that writes an XLSX workbook to disk, again without disclosure or consent. Because spreadsheet generation involves extra libraries and persistent file output, it further enlarges the operational surface for a skill that should primarily produce textual test artifacts.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

The manifest scopes the skill to generating test cases, test points, scenarios, matrices, and coverage analysis. These lines extend the skill into advising on automation frameworks, technology stacks, and mapping cases to automated scripts, which is a distinct downstream engineering activity not reflected in the manifest description.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.