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 report is unreliable and the optional Windows application remains unreviewed.

The Python workflow needs no external application. Manually inspect the campaign and sending-platform settings: the report omits compliance checks, and its parser can mistake template limits for supplied copy. Assess the optional unsigned Windows program separately before running it.

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
99% confidence
Finding

The code's main output is a presence-and-length audit of existing input, not the described campaign brief. Its static guardrails concern misleading claims, testimonials, and avoiding email transmission; they do not provide the promised CAN-SPAM and bulk-sender checklist. Local input reading and report writing are ordinary supporting operations, and no unrelated access or sending behavior 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 report omits the promised campaign copy and CAN-SPAM/bulk-sender elements.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

The script produces field-length statistics rather than the promised campaign copy and does not identify or validate CAN-SPAM or bulk-sender requirements. In a skill explicitly marketed for compliant email preparation, this omission can give users misplaced confidence and allow incomplete campaigns to proceed without required disclosures or unsubscribe mechanisms. Impact is limited because the script neither sends email nor explicitly certifies compliance, and downstream sending platforms may supply missing elements.

Content

No source excerpt is available for this finding.