ClawHub
Back to skill

Security audit

Envios

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward shipping-support instruction skill with no executable code, persistence, hidden behavior, or unrelated data access.

Installers should treat this as a localized Argentina shipping-support skill. Confirm it is intended for that business context, narrow the trigger if other order/refund/payment skills exist, and ensure only authorized staff or agents use courier accounts, WhatsApp, Google Maps, and customer addresses.

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)

Natural-Language Policy Violations

Medium
Confidence
88% confidence
Finding
The entire skill is written in Rioplatense Spanish and assumes Argentina-specific phrasing and geography, but it does not state that this locale is intentional or that language should match the user's preference. This can violate language/locale policy when the system expects user choice or explicit regional justification.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The trigger description is broad enough to activate on many general shipping-related queries without clear scope boundaries, which can cause the agent to invoke this skill in situations where more specific or authoritative logic should apply. In this skill, that mainly creates a quality and routing risk rather than direct exploitation, but it could still lead to incorrect operational guidance being given to users.

Static analysis

No suspicious patterns detected.