Back to skill

Security audit

email-designer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a plain Markdown instruction set for generating designed HTML emails, with no executable code or hidden installation behavior.

Install this only if you want a Chinese-oriented HTML email design assistant. Review or replace any Google Fonts and Unsplash URLs before sending production emails, especially for privacy-sensitive campaigns.

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
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (3)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill is written to operate in Chinese without offering user language choice, which can override user intent and cause inappropriate activation or output language mismatches. In an agent setting, forced language behavior can reduce transparency, impair user review, and increase the chance that generated content is misunderstood or misused.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The invocation condition is broad enough to match many generic requests involving email content, outlines, templates, or EDM creation. Overly broad activation can cause the skill to trigger unexpectedly, override more appropriate instructions, and steer outputs toward rigid HTML-generation behavior even when the user did not clearly request this specialized skill.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

The manifest describes an email HTML designer that generates code and templates from provided content. Line L088 explicitly requires introducing fonts via Google Fonts CDN, adding an external-network dependency in the produced output that is not necessary to fulfill the core purpose of email template generation and is not declared in the manifest scope.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.