ClawHub
Back to skill

Security audit

ab-testing

Security checks for vulnerabilities and agentic risk

Overview

This skill is a guidance-only A/B testing helper with no executable code, persistence, credential handling, or hidden behavior found.

Installers should expect this skill to guide experiment design and may let it read existing product-marketing context files to avoid repeated questions. Review those context files if they contain sensitive strategy details, but the inspected skill does not attempt to send, persist, or modify that information.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
97% confidence
Finding
The trigger description is unusually broad and includes many generic terms like "experiment," "test this change," and "comparing two approaches," which can cause the skill to activate for requests outside true A/B testing scope. Over-broad invocation is dangerous because it can route unrelated user tasks into the wrong skill, leading to inappropriate instructions, context leakage from automatically read files, or degraded agent behavior.

Vague Triggers

Medium
Confidence
96% confidence
Finding
The eval explicitly expects the skill to trigger on casual phrasing ('we want to test like 4 different CTA button colors... is that a good idea?'), which broadens activation beyond precise experimentation requests. Over-broad routing can cause the wrong skill to engage on general marketing or design discussions, leading to irrelevant guidance, missed handoff to more appropriate skills, and reduced reliability of agent behavior.

Static analysis

No suspicious patterns detected.