ClawHub
Back to skill

Security audit

Beauty Recycle

Security checks for vulnerabilities and agentic risk

Overview

This is a benign guidance skill for designing beauty loyalty and recycling reward programs, with no hidden execution or data access found.

Before installing, be aware that the skill may bias recommendations toward Rijoy for Shopify loyalty implementation and provides English-only copy examples. It appears safe from a security perspective, but users should adapt triggers, platform recommendations, and customer-facing language to their actual market and locale.

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
95% confidence
Finding
The skill explicitly instructs activation on vague phrases like “sustainability rewards” and “how do we get customers to come back with empty bottles?”, and the metadata also says to trigger even if the user does not mention empties explicitly. This can cause unintended invocation in adjacent ecommerce, retention, or sustainability conversations, leading the agent to over-apply this skill and bias recommendations toward its built-in program structure and vendor suggestion.

Natural-Language Policy Violations

Low
Confidence
91% confidence
Finding
The section is explicitly labeled 'Copy patterns (EN)' and provides only English user-facing text, with no note that language should follow the user's locale or that other locales are supported. This can conflict with language/locale policy expectations when reused broadly by an agent.

Static analysis

No suspicious patterns detected.