ClawHub
Back to skill

Security audit

Ab Test

Security checks for vulnerabilities and agentic risk

Overview

This skill is a very sparse A/B test manager that asks for an API key but does not clearly define the service, data use, or safeguards for account-changing actions.

Review carefully before installing. Only use this with a non-production or tightly scoped A/B testing API key unless the publisher documents the exact service, allowed operations, and confirmation requirements for changes to experiments.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill's invocation criteria are broad and vague (e.g., 'testing related functionality' and 'Automating ab tasks'), which can cause the agent to select this skill in contexts the user did not intend. Because the skill appears to interact with an external A/B testing system, unintended invocation could trigger actions or data handling against a live service without clear user awareness.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The documentation instructs users to provide an API key but does not clearly warn that the skill likely connects to an external service or may transmit user or business data. This lack of disclosure increases the risk of users supplying sensitive credentials or invoking the skill without understanding that external network actions and account-side changes may occur.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.