← 返回 Skills 市场
70
总下载
0
收藏
1
当前安装
1
版本数
在 OpenClaw 中安装
/install nm-gauntlet-graph-search
功能描述
Search the code knowledge graph by function, class, or type name using FTS5 full-text search with query-aware kind boosting
安全使用建议
This skill appears to do what it says (search a local .gauntlet/graph.db) but the SKILL.md expects CLAUDE_PLUGIN_ROOT and calls python3 even though the registry lists no required env or binaries. Before installing or running it: 1) verify that CLAUDE_PLUGIN_ROOT will be set to a trusted plugin checkout; 2) inspect the file scripts/graph_query.py in that repository to confirm it only reads the graph and source files you expect; 3) ensure python3 is available in a controlled/sandboxed environment; 4) only run this if you trust the plugin source or after reviewing the script — otherwise run the search in a sandbox or request the skill author to declare required env vars and binaries explicitly.
功能分析
Type: OpenClaw Skill
Name: nm-gauntlet-graph-search
Version: 1.0.0
The skill defines a workflow in SKILL.md that executes a local Python script (graph_query.py) using a shell command with user-provided input in the --query parameter. This pattern introduces a potential shell injection vulnerability if the agent does not sanitize the input. While the functionality is aligned with its stated purpose of searching a local SQLite database (.gauntlet/graph.db), the lack of explicit input handling makes it high-risk.
能力评估
Purpose & Capability
The skill's stated purpose (FTS5 search of a code knowledge graph) is consistent with the instructions to run a graph_query.py script against .gauntlet/graph.db. However, the SKILL.md expects a runtime environment (CLAUDE_PLUGIN_ROOT, python3) that the registry metadata does not declare — a minor incoherence.
Instruction Scope
Instructions are narrowly scoped to running the plugin's graph_query.py against .gauntlet/graph.db and optionally reading the matched source file. The instructions do not ask the agent to exfiltrate results to external endpoints or to read unrelated system-wide files.
Install Mechanism
There is no install spec (instruction-only), so nothing will be downloaded or written by the registry itself. Risk comes from running a local script (plugin's scripts/graph_query.py) at runtime, which is expected for this kind of plugin.
Credentials
SKILL.md uses the CLAUDE_PLUGIN_ROOT environment variable and invokes 'python3', but the registry lists no required env vars or binaries. This mismatch is concerning because the skill depends on an undeclared environment and an executable that may or may not be present — and the script executed could read arbitrary files under the plugin root.
Persistence & Privilege
The skill does not request persistent/always-on presence and does not modify other skills or global agent configuration according to the metadata.
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 nm-gauntlet-graph-search - 安装完成后，直接呼叫该 Skill 的名称或使用
/nm-gauntlet-graph-search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 the graph-search skill.
- Search code knowledge graph by function, class, or type name using FTS5 full-text search.
- Includes query-aware kind boosting for smarter search results based on the search term’s pattern.
- Displays qualified name, file path, line numbers, and relevance score in results.
- Offers to read the top result’s source file.
- Requires a pre-built `.gauntlet/graph.db`; suggests running graph-build if missing.
元数据
常见问题
Nm Gauntlet Graph Search 是什么？
Search the code knowledge graph by function, class, or type name using FTS5 full-text search with query-aware kind boosting. 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 Nm Gauntlet Graph Search？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install nm-gauntlet-graph-search」即可一键安装，无需额外配置。
Nm Gauntlet Graph Search 是免费的吗？
是的，Nm Gauntlet Graph Search 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Nm Gauntlet Graph Search 支持哪些平台？
Nm Gauntlet Graph Search 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 Nm Gauntlet Graph Search？
由 athola（@athola）开发并维护，当前版本 v1.0.0。
推荐 Skills