ClawHub
Back to skill

Security audit

Antigravity

Security checks for vulnerabilities and agentic risk

Overview

This is a simple informational Antigravity guide with no executable code, hidden behavior, or high-impact authority.

This skill appears safe to install as an informational guide. Users should still treat its product details as documentation-style guidance and only clone or install third-party skill repositories from sources they trust.

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 (3)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 39)May include surrounding context.

md
- **A**：通常通过 Git Clone 官方或社区的 Skills 仓库到指定目录，或者手动创建包含 `SKILL.md` 的文件夹。

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

L06 将触发条件描述为“提供全面介绍…当用户询问‘什么是 Antigravity’、‘如何使用 Antigravity’或需要了解其 Agent 优先理念时使用”。前两类示例较具体，但“需要了解其 Agent 优先理念时使用”边界不清，缺少排除条件或更明确的触发短语，容易扩大到泛泛的产品介绍或理念讨论。

Content

No source excerpt is available for this finding.

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 44)May include surrounding context.

md
#### 示例对话

**用户**：“帮我介绍一下 Antigravity 的 Skill 系统。”
**Agent**：“Antigravity 的 Skill 系统是一套开放标准，允许你通过 Markdown 文件教 Agent 学习新技能。比如你可以创建一个 Skill 来规范 Git 提交信息。只需在项目中创建 `.agent/skills/my-skill/SKILL.md`，写入指令，Agent 就会自动识别并执行。”

Static analysis

No suspicious patterns detected.