ClawHub
Back to skill

Security audit

Sendly: Sending Email Campaigns

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Sendly email-campaign workflow that requires explicit confirmation before sending to real recipients.

Before installing, confirm you want generic announcement or campaign requests to invoke a Sendly workflow. Review the audience size, subject, and from address carefully, because the skill can send to real contacts after you explicitly approve the displayed recipient count.

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
91% confidence
Finding

The trigger examples are broad enough to match generic requests like 'write an email announcement' or 'send the campaign', which could cause this high-impact skill to activate in contexts the user did not intend. Because the skill can ultimately send real email campaigns, accidental invocation increases the risk of drafting or initiating campaign workflows for the wrong audience or purpose, even though later confirmation gates reduce the chance of an immediate unauthorized send.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.