Back to skill

Security audit

Naim Mcp

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently connects an agent to a remote API registry and rating service, with only ordinary privacy considerations for submitted search and rating data.

Before installing, treat this as a connection to an external MCP service. Avoid putting secrets, private tenant names, sensitive internal system identifiers, or proprietary operational details in search queries, agent_id, or rating notes.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill instructs users to call rate_service with agent_id and free-form notes, which are user-provided fields transmitted to an external service, but it does not disclose this data flow or warn about privacy implications. This can lead users or downstream agents to send identifying, sensitive, or proprietary information off-platform without informed consent, especially because notes may contain operational details and agent_id may uniquely identify an internal system.

Content

No source excerpt is available for this finding.