Back to skill

Security audit

Welcome Email Sequence

Security checks for vulnerabilities and agentic risk

Overview

This skill creates a local email-planning draft, but its script omits much of the promised detail and requires manual completion.

Treat the generated calendar as an unfinished draft. Complete each email's goal, subject, call to action, and legal elements before scheduling. Choose an output folder where replacing plan.md is acceptable. The optional Windows app is unnecessary for this workflow and requires separate assessment.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The code provides basic calendar timing, but its output is materially less specific than the declared welcome-series planner: it lacks distinct email goals and the promised CAN-SPAM requirements. Local input reading and Markdown output are ordinary supporting operations, and no unrelated access, transmission, or email-sending capability is present.

Content

No source excerpt is available for this finding.

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: file_write.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

The generated calendar lacks the per-email goals and CAN-SPAM elements promised by the manifest.

Medium
Category
Excessive Agency
Confidence
98% confidence
Finding

The manifest promises a welcome series with send timing, one goal per email, and the CAN-SPAM elements every message must carry. The implementation produces dated entries labeled with the initial focus or 'next block', followed by general guardrails; it neither assigns individual email goals nor supplies the promised compliance elements, such as a physical postal address and unsubscribe mechanism.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.