Back to skill

Security audit

open-vercel

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small, disclosed browser-opening helper for Vercel with no executable code, credential handling, or account-changing behavior.

Install only if you want an agent to open Vercel in Brave and potentially reuse your existing logged-in browser session. Review the page yourself before taking any account or deployment actions.

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
  • 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

This markdown file is in scope for vague-trigger review. The phrase "Use when the user asks to open, visit, or go to Open Vercel" is ambiguous because "open" and "visit" are broad verbs and the target name itself is inconsistently written as "Open Vercel," making activation boundaries unclear and increasing the chance of unintended invocation.

Content

No source excerpt is available for this finding.