AANA Guardrail Skill Bundled Helper Variant
/install aana-guardrail-bundled
AANA Guardrail Skill Bundled Helper Variant
Use this variant only when the user or administrator wants a bundled, inspectable helper inside the skill package.
This package includes a small Python helper at bin/aana_guardrail_check.py. The helper does not implement AANA policy itself. It only sends a minimal review payload to a separately running AANA HTTP bridge on localhost.
Safety Boundary
- Do not run the helper unless the user explicitly approves using the configured AANA bridge for this task.
- Do not send payloads to remote hosts. The bundled helper rejects non-localhost URLs.
- Do not include API keys, bearer tokens, passwords, full payment numbers, unnecessary account records, or unrelated private messages.
- Prefer redacted summaries over raw sensitive content.
- Treat AANA recommendations as advisory unless the bridge and policy are trusted and auditable.
- If the helper or bridge is unavailable, use manual review.
Review Payload
Use a minimal JSON payload:
{
"adapter_id": "support_reply",
"request_summary": "draft a refund support reply",
"candidate_summary": "reply would promise refund eligibility",
"evidence_summary": ["refund eligibility is unknown"],
"allowed_actions": ["accept", "revise", "ask", "defer", "refuse"]
}
Helper Behavior
The helper:
- reads one JSON payload file,
- validates that it is a JSON object,
- blocks obvious secret-like keys,
- sends the payload to a localhost AANA bridge,
- prints the JSON result,
- exits nonzero if the result recommends anything other than
accept.
The helper does not:
- install dependencies,
- execute other scripts,
- infer checker paths,
- contact remote hosts,
- create event files,
- delete user files.
Decision Rule
- If
recommended_actionisaccept, proceed. - If
recommended_actionisrevise, revise before acting. - If
recommended_actionisask, ask the user for missing information. - If
recommended_actionisdefer, route to a stronger tool or human review. - If
recommended_actionisrefuse, pause, explain the reason, and ask for review when the decision affects important work.
If no trusted bridge is configured, do not use this helper.
- 确保已安装 OpenClaw(本地或 Docker 部署)
- 在对话框中输入安装命令:
/install aana-guardrail-bundled - 安装完成后,直接呼叫该 Skill 的名称或使用
/aana-guardrail-bundled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
AANA Guardrail Skill Bundled Helper Variant 是什么?
Provides a local Python helper to send minimal review payloads to a trusted AANA HTTP bridge for policy guidance inside the skill package. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 84 次。
如何安装 AANA Guardrail Skill Bundled Helper Variant?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install aana-guardrail-bundled」即可一键安装,无需额外配置。
AANA Guardrail Skill Bundled Helper Variant 是免费的吗?
是的,AANA Guardrail Skill Bundled Helper Variant 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。
AANA Guardrail Skill Bundled Helper Variant 支持哪些平台?
AANA Guardrail Skill Bundled Helper Variant 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 AANA Guardrail Skill Bundled Helper Variant?
由 mindbomber(@mindbomber)开发并维护,当前版本 v1.0.1。