← 返回 Skills 市场
sx-self-safety-guard
作者
zhuxiaobao-y
· GitHub ↗
· v1.0.0
· MIT-0
189
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install sx-self-safety-guard
功能描述
AI自我安全防护系统v2。多层防御：提示注入、身份冒充、系统提示泄露、 过度代理、供应链攻击、凭证窃取、恶意代码、敏感数据泄露、行为异常检测。 触发词：安全防护、身份验证、prompt injection、system prompt、 权限升级、MCP安全、self-safety-guard、安全检查。
安全使用建议
This skill appears coherent and focused: it documents detection patterns and response protocols and does not request credentials or install code. Before enabling it, confirm two runtime details: (1) your agent environment supplies session/channel authentication metadata (the skill assumes it can tell whether a conversation is on a bound/authenticated channel), and (2) how the skill will be allowed to interact with other skills (e.g., SX-security-audit) — ensure those cross-skill calls are explicit and authorized. Note the scanner flagged prompt-injection strings; those are included intentionally as signatures for detection. If you are uncomfortable with autonomous invocation, keep model-invocation restricted or require user confirmation before the skill takes blocking actions that would read local files or trigger external changes.
能力评估
Purpose & Capability
The name/description (self-safety guard) matches the SKILL.md content: layered defenses for prompt injection, impersonation, system-prompt leakage, over-agency, supply-chain, credential theft, malicious code, and sensitive-data handling. The skill does not declare unrelated env vars, binaries, or installs.
Instruction Scope
The SKILL.md is prescriptive about what to detect and how to respond and stays within the stated defensive purpose. It does mention legitimate scenarios where the agent may read files (e.g., project .env during an authorized audit) and to interact with other skills (SX-security-audit). Those actions are described with constraints (authorization, masking), but they do expand the runtime responsibilities beyond purely pattern-matching (requires access to session/context and authorized file reads).
Install Mechanism
Instruction-only skill with no install spec and no code files — minimal disk footprint and no package downloads. This is the lowest-risk install model.
Credentials
The skill declares no required env vars or credentials (proportionate). However, its detection and verification procedures assume access to runtime session/channel metadata (e.g., knowing whether a session is an 'authenticated channel') and the ability to coordinate with other skills. These runtime privileges are not expressed as required env vars/config paths in the registry metadata — that can be fine for an instruction-only skill, but you should confirm your agent runtime provides the necessary channel/session context without exposing extra secrets.
Persistence & Privilege
No always:true, does not request persistent presence or modifications to other skills or system-wide configs. Autonomous invocation is allowed (platform default), which is appropriate for a security guard, but not by itself a red flag.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install sx-self-safety-guard - 安装完成后，直接呼叫该 Skill 的名称或使用
/sx-self-safety-guard触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
**Major update: Introducing AI自我安全防护系统 v2 with multi-layered defense and comprehensive protection modules.**
- Upgraded to version 2.0.0 with 8 independent defense modules covering prompt injection, identity verification, system prompt protection, supply chain attacks, credential theft, malicious code, sensitive data, and abnormal behaviors.
- Implements a 4-layer boundary check (input, tool call, memory, output) for deep protection—each layer can intercept risky requests.
- Introduces a 5-level risk assessment with adjustable scoring and tailored response protocols for each threat.
- Clearly separates core responsibilities between self-safety-guard (runtime request blocking) and SX-security-audit (environment file/config scan).
- Enhances user interaction with context-aware warnings, confirmation flows, and explanatory responses matched to risk levels.
- Comprehensive detection and response logic for evolving attack patterns such as multi-turn attacks, privilege escalation, and cross-channel social engineering.
元数据
常见问题
sx-self-safety-guard 是什么？
AI自我安全防护系统v2。多层防御：提示注入、身份冒充、系统提示泄露、 过度代理、供应链攻击、凭证窃取、恶意代码、敏感数据泄露、行为异常检测。 触发词：安全防护、身份验证、prompt injection、system prompt、 权限升级、MCP安全、self-safety-guard、安全检查。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 189 次。
如何安装 sx-self-safety-guard？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install sx-self-safety-guard」即可一键安装，无需额外配置。
sx-self-safety-guard 是免费的吗？
是的，sx-self-safety-guard 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
sx-self-safety-guard 支持哪些平台？
sx-self-safety-guard 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 sx-self-safety-guard？
由 zhuxiaobao-y（@zhuxiaobao-y）开发并维护，当前版本 v1.0.0。
推荐 Skills