ClawHub
Back to skill

Security audit

email-campaign-builder

Security checks for vulnerabilities and agentic risk

Overview

The bundled workflow has limited local access, but its incomplete report should not be treated as proof that an email is ready to send.

Use this for draft preparation and manually review the campaign and sending-platform requirements. The report neither generates campaign copy nor verifies compliance, and its template parsing is unreliable. Choose an output folder where replacing an existing report is acceptable. The optional Windows app is unnecessary for this workflow and requires a separate trust decision.

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
  • 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
99% confidence
Finding

The script's substantive output consists of field lengths, missing-field notices, and three static guardrails. It does not output or generate campaign copy and has no checks or annotations for CAN-SPAM or bulk-sender requirements. These omissions materially distinguish its implemented purpose from the declared campaign-building and compliance-marking functionality. Local input reading and report writing are supporting implementation details, not undeclared capabilities.

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 brief omits the CAN-SPAM and bulk-sender elements promised by the manifest.

Medium
Category
Excessive Agency
Confidence
98% confidence
Finding

The generated report checks field presence and length but omits the CAN-SPAM and bulk-sender checklist promised by the skill description, including unsubscribe mechanisms, a valid physical postal address, and applicable sender-authentication requirements. In a skill explicitly offered for compliant marketing emails, this omission could lead users to mistake an incomplete brief for adequate compliance guidance, risking noncompliant sends and deliverability problems. This is a compliance-safety gap rather than a direct code-execution vulnerability; its impact is limited because the script does not send or schedule email.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.