ClawHub
Back to skill

Security audit

smithery-ai-cli

Security checks for vulnerabilities and agentic risk

Overview

This skill is a legitimate Smithery CLI helper, but its trigger is broad enough to involve external services, installs, long-lived connections, and tool calls when the user may not have explicitly asked for that level of access.

Install only if you intend to use Smithery as a broker for MCP tools and integrations. Before authorizing services or calling tools, confirm the namespace, connection ID, token policy, permissions, and whether the target tool can modify external data such as issues, messages, records, or cloud resources.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill description is extremely broad and explicitly invites use for discovering, connecting to, installing, and interacting with many external services, which can cause the agent to invoke this skill for loosely related user requests. That over-triggering increases the chance of unnecessary access to external systems, unintended installation or connection workflows, and expansion of the agent's authority beyond what the user specifically intended.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.