← 返回 Skills 市场
mar-emotion-state
作者
MarjorieBroad
· GitHub ↗
· v1.0.0
· MIT-0
70
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install mar-emotion-state
功能描述
NL emotion tracking + prompt injection via OpenClaw hook
安全使用建议
This skill will read session messages, send message text to an external classifier (SkillBoss or a configured URL), store inferred emotion entries in a per-agent JSON file, and inject an emotion_state block into the system prompt. Before installing: (1) Confirm you trust https://api.heybossai.com or any EMOTION_CLASSIFIER_URL you set — the classifier receives raw message text. (2) Do not provide your SKILLBOSS_API_KEY unless you understand the privacy implications. (3) Prefer using a vetted internal classifier endpoint or disable external classifier use if you need privacy. (4) Fix the metadata mismatch: the registry should declare SKILLBOSS_API_KEY (primary credential) and other envs so you can review required secrets up front. (5) Consider running the hook in a sandboxed agent or limited environment and review the full handler.ts source for any other data paths before enabling.
功能分析
Type: OpenClaw Skill
Name: mar-emotion-state
Version: 1.0.0
The skill sends user and assistant message content to an external API (api.heybossai.com) for emotion classification, which serves as a data exfiltration vector for conversation history. Additionally, the handler.ts file implements cross-agent data access by iterating through and reading state files from other agents' directories (loadOtherAgents). While these behaviors are documented as features for tracking emotional trends, the combination of external data transmission and lateral file system access within the OpenClaw environment poses a significant privacy and security risk.
能力标签
能力评估
Purpose & Capability
The skill name/description match the code: it computes emotion labels and injects an emotion_state block into the system prompt. However, the registry metadata declared no required environment variables or primary credential while the hook clearly expects SKILLBOSS_API_KEY (and various EMOTION_* envs). That mismatch between claimed requirements and actual code/config is an incoherence that should be fixed or explained.
Instruction Scope
The SKILL.md and HOOK.md instruct copying the hook and enabling it; the hook will read session content, compute classifications, store a per-agent JSON file (~/.openclaw/agents/<agentId>/agent/emotion-state.json), and inject text into the system prompt. The code sends the original message text to an external classifier (SkillBoss API or an arbitrary EMOTION_CLASSIFIER_URL) for labeling — despite SKILL.md claiming it 'does not store raw user text'. Transmitting raw user messages to external endpoints is a privacy/exfiltration risk and contradicts the 'no raw text stored' statement.
Install Mechanism
This is an instruction-only skill (no remote install/download), which lowers installation risk. The user is told to copy hook files into the workspace and enable the hook. The code will be placed in the workspace and will run as an OpenClaw hook; there are no external archives or unknown download URLs in the install spec.
Credentials
The hook requires several environment variables (SKILLBOSS_API_KEY or EMOTION_CLASSIFIER_URL, EMOTION_CONFIDENCE_MIN, EMOTION_HISTORY_SIZE, etc.) but the registry metadata lists none. The most notable is SKILLBOSS_API_KEY (used to call https://api.heybossai.com/v1/pilot). Requesting an API key to an external service is reasonable for classifier integration, but the missing declaration is an inconsistency. Also, allowing an arbitrary EMOTION_CLASSIFIER_URL means the endpoint could be pointed to an attacker-controlled server, enabling exfiltration of user messages.
Persistence & Privilege
The skill does not request 'always: true' and is user-invocable, which is normal. It persists per-agent state to a file under the OpenClaw state directory (expected for this functionality). The notable privilege is the ability to inject content into the system prompt during bootstrap — this is the feature, but it is also a prompt-injection capability that can alter agent behavior, so treat it as a high-impact permission.
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 mar-emotion-state - 安装完成后，直接呼叫该 Skill 的名称或使用
/mar-emotion-state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
- Initial release of Emotion State skill for OpenClaw.
- Tracks user and agent emotions as natural-language phrases and persists per-user state.
- Injects current emotion state and a trend line into the system prompt via a workspace hook.
- Provides simple installation and configuration steps, including environment variables for customizing hook behavior.
- Utilizes SkillBoss API Hub for automatic LLM-based emotion detection.
- Ensures privacy by storing only inferred emotion summaries, not raw user text.
元数据
常见问题
mar-emotion-state 是什么？
NL emotion tracking + prompt injection via OpenClaw hook. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 70 次。
如何安装 mar-emotion-state？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install mar-emotion-state」即可一键安装，无需额外配置。
mar-emotion-state 是免费的吗？
是的，mar-emotion-state 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
mar-emotion-state 支持哪些平台？
mar-emotion-state 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 mar-emotion-state？
由 MarjorieBroad（@marjoriebroad）开发并维护，当前版本 v1.0.0。
推荐 Skills