← 返回 Skills 市场
Pre Flight
作者
Wyatt Benno
· GitHub ↗
· v1.0.6
· MIT-0
380
总下载
1
收藏
1
当前安装
7
版本数
在 OpenClaw 中安装
/install pre-flight
功能描述
Stop your agent from doing things you didn't authorize. ICME checks every consequential action against your policy before it executes — email, transactions,...
安全使用建议
PreFlight is coherent for its purpose: it will call an external ICME API and needs your ICME_API_KEY and ICME_POLICY_ID to operate. Before installing, decide whether it's acceptable for your agent to send descriptions of proposed actions (which may include recipients, amounts, file paths, or other sensitive text) to a third-party service. If you proceed: (1) limit the data the agent includes in action descriptions (use redaction or abstract descriptions where possible), (2) use a policy_id scoped to the minimal resources, (3) rotate and scope the API key, and (4) review ICME's privacy/payment terms (the skill references paid check endpoints and an x402 payment flow). The small metadata mismatch (primaryEnv present in SKILL.md but not in registry metadata) is not a functional issue but you may want to confirm the canonical primary credential before onboarding.
功能分析
Type: OpenClaw Skill
Name: pre-flight
Version: 1.0.6
The 'pre-flight' skill is a security guardrail system designed to verify agent actions against user-defined policies using automated reasoning. It provides tools for logical consistency checking, relevance screening, and policy verification via the ICME API (api.icme.io). The skill includes instructions for the agent to 'fail closed' and report policy violations to the user, which are security-enhancing behaviors. No evidence of malicious intent, unauthorized data exfiltration, or obfuscation was found; the skill appears to be a legitimate tool for managing agent safety.
能力评估
Purpose & Capability
Name/description claim to enforce policy checks before consequential actions aligns with required environment variables (ICME_API_KEY, ICME_POLICY_ID) and the SKILL.md instructions which call an external ICME API. One minor registry inconsistency: the SKILL.md metadata lists primaryEnv: ICME_API_KEY while the registry metadata earlier reported no primary credential — this is superficial and does not change capability alignment.
Instruction Scope
The SKILL.md instructs the agent to POST plain-English action descriptions and plans to ICME endpoints (checkLogic, checkRelevance, checkIt). That is coherent for a guardrail. However, because the agent will typically send descriptions of proposed actions, those requests can include sensitive data (recipients, file paths, transaction details). The skill does not instruct reading arbitrary host secrets or system files, but it does recommend running relevance checks 'before every action', which could cause frequent outbound transmission of action text.
Install Mechanism
Instruction-only skill with no install spec and no code files. No packages or archives are downloaded or extracted by the skill itself, minimizing installation risk.
Credentials
Requested env vars (ICME_API_KEY, ICME_POLICY_ID) are appropriate and limited to the external policy service the skill integrates with. There are no unrelated credentials or config paths requested. Consider that the API key grants the external service the ability to receive action descriptions tied to your policy_id and produce verdicts; if those action descriptions contain sensitive data, you are effectively sending that data to the provider.
Persistence & Privilege
always is false and the skill is instruction-only (no background persistence or config modification). The skill can be invoked autonomously by the agent (disable-model-invocation is false), which matches its purpose as a runtime guardrail. It does not request system-wide or other-skills' configuration access.
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 pre-flight - 安装完成后，直接呼叫该 Skill 的名称或使用
/pre-flight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
v1.0.6
pre-flight 1.0.6 changelog
- Added _meta.json file for enhanced metadata support.
- No changes to core functionality or documentation.
v1.0.5
Version 1.0.5
- Expanded feature set: now includes structured value checks, ZK (zero-knowledge) proof verification, and policy iteration tools
- Documentation updates: improved tool descriptions, usage instructions, and clearer guidance on endpoints and authentication
- Added new paid endpoint: checkItPaid allows action checks with per-call payment (no account required)
- Refined overall documentation for clarity and conciseness, especially around when and how to use each tool
v1.0.4
**Adds free relevance screener tool.**
- Introduced `checkRelevance` (free, requires API key) to screen actions against your policy and avoid unnecessary paid checks.
- Updated documentation to cover three tools: checkLogic (logic contradiction detector), checkRelevance (relevance screener), and checkIt (policy enforcement).
- checkRelevance shows which policy variables an action touches and recommends when to run `checkIt`.
- No changes to setup or paid guardrail logic; only clarifies when and how to use each tool.
v1.0.3
Initial public release.
- Added all core files for the pre-flight skill, including setup, documentation, and Git repo initialization.
- Provides logic contradiction detection (free) and policy-based action checking (paid) for agent safety.
- Includes detailed instructions for both quick start and advanced guardrail setups.
- Requires ICME_API_KEY and ICME_POLICY_ID environment variables for policy enforcement.
v1.0.2
updated readme with free endpoint
v1.0.1
- Added a README.md file for the skill.
- No changes to existing logic or configuration.
v1.0.0
- Initial release of pre-flight skill.
- Checks every consequential agent action against your ICME policy before execution (e.g., email, transactions, file ops, external calls).
- Define policy rules in plain English; get results (`SAT`/`UNSAT`) in under a second.
- Provides clear guidance for blocked actions and handling insufficient credits.
- Includes setup instructions and usage examples for integrating ICME Guardrails.
元数据
常见问题
Pre Flight 是什么？
Stop your agent from doing things you didn't authorize. ICME checks every consequential action against your policy before it executes — email, transactions,... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 380 次。
如何安装 Pre Flight？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install pre-flight」即可一键安装，无需额外配置。
Pre Flight 是免费的吗？
是的，Pre Flight 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Pre Flight 支持哪些平台？
Pre Flight 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 Pre Flight？
由 Wyatt Benno（@wyattbenno777）开发并维护，当前版本 v1.0.6。
推荐 Skills