Back to skill

Security audit

openspec-bootstrap

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent OpenSpec bootstrap guide that installs/initializes OpenSpec and customizes project config, with no evidence of hidden or malicious behavior.

Before installing, confirm you are comfortable with a global npm install of OpenSpec and with the skill generating or overwriting OpenSpec-related project files. Run it in a clean git worktree so changes can be reviewed or reverted.

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 (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The invocation description and trigger examples are written only in Chinese, indicating a language-specific interaction model. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is explicitly justified, which it is not here.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The markdown presents zh-CN as the example language for generated artifacts, which can imply a preferred or default locale. Because no user opt-in or locale-selection guidance is included here, this risks violating the language/locale policy for skills that should not force a specific language.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.