Back to skill

Security audit

ab-test-calculater

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local A/B test calculator whose packaged script matches its stated statistical-analysis purpose and does not show hidden data access, networking, persistence, or destructive behavior.

Install this if you want a local, zero-dependency helper for A/B test calculations. Provide only the experiment metrics needed for the analysis, and double-check the statistical assumptions before making important product or business decisions.

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
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (3)

Concealed Executable Artifact

High
Category
Supply Chain
Confidence
100% confidence
Finding

An executable nested in a document or hidden/disguised artifact can evade ordinary extension-based review while still being available to the skill at runtime.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger list contains broad, common phrases such as '哪个版本更好' and 'ab test' that may match ordinary user requests outside the intended skill scope, causing unintended invocation. While not directly enabling code execution or data exfiltration, overly broad routing can misfire the skill, confuse users, and increase the chance that this skill intercepts queries better handled by other tools.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

The description promises a one-line plain-language conclusion and presents the skill primarily in Chinese/English bilingual wording, but does not state that the user can choose the response language. This can be a language/locale policy concern if the skill defaults to a language style without explicit user preference.

Content

No source excerpt is available for this finding.