Back to skill

Security audit

upsell-offer-designer

Security checks for vulnerabilities and agentic risk

Overview

This needs review because its script produces incorrect prices and does not implement the approval safeguards it promises.

Do not rely on generated customer quotes until pricing, template parsing and approval handling are corrected. Independently verify prices, approvals and offer terms before sending. The optional Windows application requires a 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
96% confidence
Finding

The reported omission of approval thresholds undermines the skill's explicit approval-safety guarantee, potentially allowing users to mistake unchecked offers for authorized ones. The reported markup error and missing buyer-facing terms could also produce materially incorrect quotes; however, the implementation was not provided for independent verification, and the documented human review step reduces exposure.

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 documented 40% markup is implemented as a 40× price multiplier.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

The documented 40% markup is applied as a 40× multiplier, producing a first-tier price of $4,800 instead of $168 on a $120 base cost. This is a business-logic integrity flaw rather than a code-execution vulnerability, but the buyer-facing offer-design context makes it consequential: generated quotes could cause substantial overpricing, lost sales, or customer disputes. The report's discount and approval guardrails do not validate or correct the underlying calculation.

Content

No source excerpt is available for this finding.