← 返回 Skills 市场
Olvid Channel
作者
jmartel-olvid
· GitHub ↗
· v0.1.0
2013
总下载
1
收藏
1
当前安装
14
版本数
在 OpenClaw 中安装
/install olvid-channel
功能描述
Add a native Olvid channel in OpenClaw.
安全使用建议
This skill appears to do what it claims: it connects your OpenClaw agent to an Olvid daemon using a client key and daemon URL. Before installing: 1) Treat the client key as a secret — prefer entering it in plugin config rather than exporting OLVID_CLIENT_KEY globally if you want scoped usage. 2) Confirm the daemonUrl points to a daemon you control (e.g., localhost) and not an untrusted remote endpoint. 3) Note the plugin writes attachments to /tmp (temporary files) and records session metadata in the OpenClaw session store. 4) The provided package-lock.json contains many transitive npm packages (including large cloud SDKs) — if you have strict supply-chain or minimal-deps requirements, inspect the lockfile or install source from the official GitHub repo (https://github.com/olvid-io/openclaw-channel-olvid) and/or build from pinned dependencies. 5) If you want higher assurance, review the referenced GitHub repo and ensure the published package matches the source.
功能分析
Type: OpenClaw Skill
Name: olvid-channel
Version: 0.1.0
The OpenClaw AgentSkills skill bundle for Olvid Channel appears benign. It integrates Olvid as a communication channel, handling message sending and receiving, including media attachments. The skill accesses environment variables (`OLVID_CLIENT_KEY`, `OLVID_DAEMON_TARGET`) for legitimate configuration and uses `/tmp/olvid-attachments` to store incoming media, which is standard for its stated purpose. No evidence of intentional data exfiltration, malicious execution, persistence mechanisms, or prompt injection attempts in the `SKILL.md` or code was found. All observed functionalities are aligned with the plugin's description.
能力评估
Purpose & Capability
Name/description match the implementation: code implements an OpenClaw channel that connects to an Olvid daemon, sends/receives messages, handles attachments, and exposes configuration for daemonUrl and clientKey.
Instruction Scope
SKILL.md is high-level and points to external docs; runtime code only accesses OpenClaw runtime APIs, the Olvid daemon (user-configured URL), and local filesystem for saving attachments (/tmp/olvid-attachments). It does not instruct the agent to read unrelated host files or exfiltrate data to unexpected external endpoints.
Install Mechanism
There is no install spec in registry metadata (installation is via hub/local package). The package files show normal npm dependencies (e.g., @olvid/bot-node, zod) and a package-lock.json that pulls many transitive packages from the npm registry. No downloads from arbitrary URLs or extract-from-unknown-server steps are present, but the transitive dependency tree is large — review if you have a strict supply-chain policy.
Credentials
The plugin uses Olvid-specific credentials (clientKey, daemonUrl) and will optionally read OLVID_CLIENT_KEY and OLVID_DAEMON_TARGET from the environment for the default account. It does not request unrelated credentials. Be aware that OLVID_CLIENT_KEY env var (if present) will be picked up automatically for the default account.
Persistence & Privilege
The skill does not request always:true and does not modify other skills. It runs a long-lived monitor (connector) to keep a session with the Olvid daemon — this is expected for a channel plugin and within its scope.
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 olvid-channel - 安装完成后，直接呼叫该 Skill 的名称或使用
/olvid-channel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
v0.1.0
- Updated package.json (details not provided).
- No user-facing or documentation changes in this release.
v0.0.15
- Removed tool documentation and tool list from SKILL.md.
- Deleted the src/agent_tools.ts file.
- Updated package.json and src/channel.ts for alignment with recent changes.
- General documentation in SKILL.md has been streamlined.
v0.0.14
- Internal refactoring: removed unused files src/actions.ts and src/directory.ts.
- Updated core source files (package.json, src/agent_tools.ts, src/channel.ts) to streamline implementation.
- No user-facing changes or new features.
v0.0.13
- Removed detailed action API documentation from SKILL.md, focusing documentation on tool-based usage.
- Kept the list and descriptions of top-level Olvid tools available via the skill.
- Installation, target examples, publishing, and contact sections remain unchanged.
v0.0.12
olvid-channel 0.0.12
- Removed `olvid_identity_set_photo` and `olvid_identity_photo_set` tools from documentation.
- Updated and refined the SKILL.md to match current tool support.
- Minor internal changes to agent tool definitions and channel handling.
v0.0.11
- Expanded and reorganized documentation to clarify usage, including new sections on targets, directory, and actionable examples.
- Added detailed JSON examples for group management, reactions, sending messages, and sending attachments.
- Updated and clarified the tool list, including new and renamed agent tools and their parameters.
- Introduced new files to support actions and directory features.
- Improved guidance on how to address Olvid entities (contacts, discussions, groups) and format targets.
v0.0.10
- Updated dependencies in package.json and package-lock.json.
- Improvements and refactoring in src/channel.ts and src/monitor.ts.
- Version bump to 0.0.10.
v0.0.9
- Added instructions for sending messages and media to Olvid discussions using the OpenClaw CLI.
- Updated documentation in SKILL.md to reflect new message sending capabilities.
- Improved clarity and structure in the feature and tool descriptions.
- Version bumped to 0.0.0-a9.
v0.0.8
- Updated dependencies in package.json.
- Refactored code in src/tools.ts for improvements or maintenance.
- No user-facing changes or documentation updates.
v0.0.7
- Updated dependencies in package.json.
- Minor internal changes to src/tools.ts. No user-facing functionality changes.
- No changes to documentation or skill features.
v0.0.6
- Improved internal logic in agent tools for better reliability.
- Updated monitor and message sending modules for maintenance and bug fixes.
- Refreshed dependencies in package.json for compatibility and stability.
- No changes to documentation or user-facing tool usage.
v0.0.5
- Added detailed documentation and usage instructions in the new README.md and expanded SKILL.md.
- Introduced new source files for agent tools and channel management.
- Updated metadata and homepage information in SKILL.md.
- Refined and documented all available Olvid tools and their API parameters.
- Improved project configuration with tsconfig.json and package-lock.json.
v0.0.0
Initial release of the Olvid Channel plugin for OpenClaw.
- Adds native support for Olvid as a messaging channel in OpenClaw.
- Provides post-quantum, end-to-end encrypted agent-to-agent messaging.
- Ensures server-blind security: messages stay unreadable even if the database is compromised.
v0.0.4
- Initial release of the Olvid Channel Plugin for OpenClaw.
- Adds support for encrypted agent-to-agent messaging using Olvid.
- Provides post-quantum, end-to-end encryption for maximum message security.
- Ensures server-blind communication: messages remain unreadable even if the database is compromised.
- Includes links to Olvid and bot documentation for further reference.
元数据
常见问题
Olvid Channel 是什么？
Add a native Olvid channel in OpenClaw. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 2013 次。
如何安装 Olvid Channel？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install olvid-channel」即可一键安装，无需额外配置。
Olvid Channel 是免费的吗？
是的，Olvid Channel 完全免费（开源免费），可自由下载、安装和使用。
Olvid Channel 支持哪些平台？
Olvid Channel 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 Olvid Channel？
由 jmartel-olvid（@jmartel-olvid）开发并维护，当前版本 v0.1.0。
推荐 Skills