Use it to define audit records, approval requirements, replay data, and review rules for AI actions that may change data, contact people, or trigger important processes.

It makes risky actions traceable before, during, and after execution. Approvals, confirmations, human overrides, and failures can be tied to the responsible person and workflow.

How xiaojilele-glitch/WhyBuddy configures Kiro

Q: What is WhyBuddy web-aigc-high-risk-node-audit-requirements.md?

An audit checklist for high-risk steps in a web-based AI workflow. It covers actions such as calling outside services, writing to databases or vector stores, sending messages, changing permissions, or submitting transactions.

Reuse

Borrowing it

Nothing to install: this file belongs to xiaojilele-glitch/WhyBuddy. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/xiaojilele-glitch/WhyBuddy/main/.kiro/steering/web-aigc-high-risk-node-audit-requirements.md

Clone the repo

git clone --depth 1 https://github.com/xiaojilele-glitch/WhyBuddy

Made for: Kiro.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/xiaojilele-glitch/whybuddy/web-aigc-high-risk-node-audit-requirements/github.svg)](https://agentmods.dev/instructions/xiaojilele-glitch/whybuddy/web-aigc-high-risk-node-audit-requirements)

Your own site

<a href="https://agentmods.dev/instructions/xiaojilele-glitch/whybuddy/web-aigc-high-risk-node-audit-requirements"><img src="https://agentmods.dev/badge/instructions/xiaojilele-glitch/whybuddy/web-aigc-high-risk-node-audit-requirements/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/xiaojilele-glitch/whybuddy/web-aigc-high-risk-node-audit-requirements"><img src="https://agentmods.dev/badge/instructions/xiaojilele-glitch/whybuddy/web-aigc-high-risk-node-audit-requirements.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,817 This file is loaded in full into every session.

When invoked 2,817 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.02817	$0.02817
Opus 5.5	$0.01127	$0.01127
Sonnet 5.5	$0.00563	$0.00563
Haiku 4.5	$0.00282	$0.00282

Measured 1mo ago against content hash 4718b7e865de, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

WhyBuddy web-aigc-high-risk-node-audit-requirements.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.kiro/steering/web-aigc-high-risk-node-audit-requirements.md · 227 lines

How it starts

The opening of the file, as written. The whole thing — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Web-AIGC 高风险节点审计要求矩阵

1. 文档目的

本文档用于为 Web-AIGC 平台中的高风险节点补齐统一审计要求，确保以下目标可以落地：

高风险动作在执行前、执行中、执行后均可追踪
审批、二次确认、人工覆盖、驳回、终止等动作具备责任归属
关键节点调用可回放、可核验、可追责
后续落地到 permissions、audit、tasks、replay 时具备统一字段基线

本文档是 .kiro/specs/web-aigc-platform-security-governance 中“为高风险节点补齐审计要求”的治理产物，面向后续实现、联调、验收使用。

2. 适用范围

本要求适用于具备以下任一特征的节点：

对外调用第三方服务或外部工具
对内部系统、数据库、向量库、事务系统产生写操作
向用户、IM、邮件、Webhook 等通道发送通知或触达
可能产生数据出站、权限提升、资金/流程提交、不可逆变更
需要人工审批、人工确认、人工驳回、人工覆盖

3. 高风险节点类别

3.1 一级高风险：必须审批或二次确认

mcp
internal_api
passthrough_api
message_notification
transaction_flow
vector_insert
vector_update
vector_delete

3.2 二级高风险：按场景触发审批

open_page
open_report
open_dashboard
file_generation
file_translation
document_search
web_search

说明：

若二级节点涉及敏感数据、跨租户访问、批量操作、对外发送、自动发布，则按一级高风险处理。
若节点最终只读、无数据出站、无副作用，可仅要求完整审计，不强制审批。

4. 审计字段总要求

所有高风险节点，无论是否最终执行成功，至少必须写入以下审计字段。

字段	说明
`auditId`	审计记录唯一标识
`traceId`	跨服务链路追踪标识
`workflowId`	所属工作流实例 ID
`taskId`	所属任务/任务片段 ID
`nodeId`	当前节点 ID
`nodeType`	当前节点类型
`riskLevel`	风险等级，如 `high` / `critical`
`tenantId`	租户标识，若系统支持多租户则必填
`operatorType`	触发主体类型，如 `agent` / `user` / `system`
`operatorId`	执行主体 ID
`actingAgentId`	代表执行的 agent ID，适用于 agent 代办
`requestSource`	调用来源，如 UI、workflow engine、A2A、API
`permissionContext`	权限上下文摘要，如 token、role、policy 快照引用
`approvalStatus`	`not_required` / `pending` / `approved` / `rejected` / `expired`
`confirmationMode`	`none` / `second_confirm` / `human_approval`
`targetSummary`	调用目标摘要，如服务名、工具名、目标资源
`inputSummary`	输入摘要，需脱敏，不得原样泄露敏感内容
`sensitiveFlags`	敏感标签，如 PII、财务、密钥、跨租户
`startedAt`	开始时间
`completedAt`	完成时间
`resultStatus`	`succeeded` / `failed` / `cancelled` / `blocked`
`resultCode`	结果码或错误码
`resultSummary`	结果摘要，需脱敏
`sideEffectLevel`	副作用级别，如 `read` / `write` / `external_send` / `irreversible`
`replayRef`	回放引用，如事件流、请求快照、工件地址
`retentionClass`	留存等级，如 `short` / `default` / `extended`

Read the full file on GitHub · 227 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

1mo ago First seen · 227 lines · 2,817 tokens per session scan A 4718b7e865de

Subscribe to this mod's changes

WhyBuddy web-aigc-high-risk-node-audit-requirements.md is an instructions file published in the GitHub repository xiaojilele-glitch/WhyBuddy (380 stars, last pushed 1mo ago), licensed MIT. It adds 2,817 tokens to every session, about $0.0113 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-23.

Project management Security ai ai-agent ai-agents anthropic chatgpt claude

WhyBuddy web-aigc-high-risk-node-audit-requirements.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
WhyBuddy web-aigc-high-risk-node-audit-requirements.mdxiaojilele-glitch/WhyBuddy	Instructions file	380	1mo ago	MIT	A	2,817	Kiro
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

WhyBuddy: Instructions file for Kiro