ClawHub
Back to skill

Security audit

Build beautiful interactive Node.js command-line apps with @clack/prompts.

Security checks for vulnerabilities and agentic risk

Overview

This skill is a documentation-only guide for building Node.js CLI prompts with @clack/prompts.

This appears safe to install as documentation for @clack/prompts. As with any CLI-building helper, review any generated app logic that collects secrets, runs subprocesses, installs npm packages, or changes files.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · references/api.md (reported line 114)May include surrounding context.

md
### confirm(options): Promise<boolean | symbol>

Yes/no confirmation. Returns `true` or `false`.

| Option | Type | Description |
|--------|------|-------------|

Static analysis

No suspicious patterns detected.