ClawHub
Back to skill

Security audit

Email Sequence

Security checks for vulnerabilities and agentic risk

Overview

This skill only guides an agent to draft structured marketing email sequences and does not request system access, persistence, credentials, or hidden execution.

Installers should treat this as a benign copywriting aid. Before using generated campaigns, users should still ensure claims are truthful, targeting is appropriate, and emails comply with applicable unsubscribe, consent, and marketing rules.

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

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
85% confidence
Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · SKILL.md (reported line 60)May include surrounding context.

md
- [ ] Do not ask in every email — give value first; pushing too early kills the sequence
- [ ] Do not forget the exit condition — emailing converted users "buy now" erodes trust
- [ ] Do not stuff multiple CTAs — one action per email or none gets taken
- [ ] Do not judge by opens alone — tie each email to the step it's meant to drive

## Based On

Static analysis

No suspicious patterns detected.