Back to skill

Security audit

Bolt New

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only Bolt.new usage guide with no executable code or hidden agent behavior, though users should be careful before publishing generated apps publicly.

Installers should treat this as a Chinese-language Bolt.new guide. Before using any one-click deploy workflow, confirm the app is meant to be public and remove secrets, API keys, private sample data, and unfinished internal content.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The file consistently presents the skill description and instructions in Chinese, but it does not indicate that the language is optional or limited to a Chinese-speaking audience. Per the policy, forcing a specific language without user opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill promotes one-click deployment to a public Netlify URL but does not clearly warn users that this can expose unfinished applications, embedded secrets, test data, or internal prototypes to the public internet. In a developer-assistance context, this omission increases the risk of accidental data exposure and insecure publication of code or services.

Content

No source excerpt is available for this finding.