ClawHub
Back to skill

Security audit

Brevo

Security checks for vulnerabilities and agentic risk

Overview

This Brevo skill is coherent and disclosed, but it controls authenticated email/contact workflows and optional automations that users should approve carefully.

Install this only if you intend to let Maton access your Brevo account. Review OAuth scopes, confirm every write or send action, be especially careful with campaign sends and deletions, and do not create functions, triggers, destinations, or watch --exec handlers unless you explicitly want ongoing automation and understand what data will flow where.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (1)

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill is nominally for Brevo API access, but it embeds extensive generic function, trigger, destination, and local watch --exec automation guidance that goes far beyond simple Brevo integration. Even though the document contains many safety warnings, these sections expand the operational capability exposed through the skill and create additional paths for code execution, persistent event forwarding, and unattended actions, increasing the attack surface and the chance an agent misuses dangerous non-Brevo features under the cover of this skill.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.