ClawHub
Back to skill

Security audit

Sending Email Campaigns

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Sendly email-campaign workflow with clear safeguards before anything is sent to real recipients.

Before installing, confirm you intend to use Sendly for email marketing and review the audience count, subject, and sender address carefully before approving a final send.

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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill description includes broad activation phrases such as 'write an email announcement,' 'prepare a campaign,' and 'send the campaign,' which can match loosely related user requests and cause the skill to be invoked in contexts where the user did not intend a real email-marketing workflow. Because this skill can progress toward actions that affect real recipients, mistaken invocation increases the chance of confusing the user, selecting an unintended audience, or nudging toward a send flow unnecessarily.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.