ClawHub
Back to skill

Security audit

Email Flows

Security checks for vulnerabilities and agentic risk

Overview

This skill only gives SaaS email marketing guidance and does not request sensitive access, persistence, or execution authority.

Before installing, note that this skill is best suited for SaaS lifecycle email strategy rather than generic one-off email writing. It appears safe to use as an advisory writing/planning aid and should not be given direct email-platform sending or account access unless you separately choose to do so.

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 manifest description says to use the skill when someone wants help with 'email marketing, drip campaigns, or email automation,' which is broad everyday phrasing rather than a narrowly scoped trigger. It does not provide clear boundaries or exclusion conditions for when this skill should activate versus other marketing or writing-related skills.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.