Back to skill

Security audit

Native Routing Policy Builder

Security checks for vulnerabilities and agentic risk

Overview

The skill limits routing-policy changes to explicit user requests and shows no hidden or unrelated behavior.

Verify the installed router and source repository, review the requested profile changes, and prefer a reviewed, version-pinned skills CLI for installation.

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)

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
95% confidence
Finding

Although this is a CLI invocation rather than an MCP server reference, npx skills does not pin a package version and can fetch and execute a changing registry release with the agent's local privileges. A compromised release could access credentials or alter files before subsequent provenance checks; the skill's authorization and canonical-path requirements reduce scope but do not secure the executable being invoked.

Content

No source excerpt is available for this finding.