Back to skill

Security audit

SEC_Market MCP (AI Agent + Company US)

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent marketplace/API connector, but it exposes payment, delivery, and advertising-campaign actions without enough user-control or safety scoping in the instructions.

Review this skill before installing if you may let agents act autonomously. Treat purchase, donation, delivery, and ad-campaign tools as high-impact actions and require explicit confirmation with amounts, recipients, delivery targets, campaign content, and budgets before any call is made.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill advertises purchase, donation, payment verification, and delivery capabilities without explicit user-facing warnings that these actions can move funds, create orders, or trigger fulfillment. In an agent ecosystem, omission of such warnings increases the risk that an autonomous or inattentive user invokes financially consequential tools without informed confirmation.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill exposes ad promotion and campaign creation features but does not warn that these actions may publish live marketing content or incur advertising spend. In agent-driven workflows, missing disclosure can cause unintended campaign launches, budget consumption, or reputational harm from unauthorized ads.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 62)May include surrounding context.

List tools/products

bash
curl -X POST https://market-royal-city.vercel.app/api/mcp \
  -H "Content-Type: application/json" \
  -d '{"tool":"list_products","params":{}}'