ClawHub
Back to skill

Security audit

Email Sender

Security checks for vulnerabilities and agentic risk

Overview

This email-sending skill is mostly transparent, but it enables outbound email, attachments, and batch campaigns without clear confirmation or abuse-prevention guardrails.

Review this skill carefully before installing. Use it only where outbound email is intended, recipients and attachments can be checked before sending, and SMTP/API credentials are scoped appropriately. Be especially cautious with batch campaigns, automated notifications, sensitive files, and compliance obligations such as consent and anti-spam 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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill describes email sending, attachments, HTML templates, and batch campaigns but does not warn users about privacy, confidentiality, phishing/spoofing, misdelivery, or bulk-email abuse risks. Because the skill enables external transmission of data, missing warnings and safeguards increase the likelihood that an agent could send sensitive content or perform high-risk bulk actions without appropriate caution.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill's invocation guidance uses broad triggers such as 'User wants to send an email' and 'Automated notifications' without scoping, approval requirements, or exclusions. In an agent setting, this can cause over-invocation for sensitive or ambiguous requests, leading to unintended outbound communication, disclosure of private data, or spam-like behavior.

Content

No source excerpt is available for this finding.