AI工作流:敏感信息扫描 是 AI Skill Hub 本期精选Agent工作流之一。综合评分 7.5 分,整体质量较高。我们推荐使用将其纳入你的 AI 工具库,帮助提升工作效率。
Find and redact secrets in AI coding agent histories (Claude Code, and more),帮助开发者发现和隐藏敏感信息,提高代码安全性和透明度。
AI工作流:敏感信息扫描 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
Find and redact secrets in AI coding agent histories (Claude Code, and more),帮助开发者发现和隐藏敏感信息,提高代码安全性和透明度。
AI工作流:敏感信息扫描 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
# 方式一:pip 安装(推荐)
pip install agent-sweep
# 方式二:虚拟环境安装(推荐生产环境)
python -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install agent-sweep
# 方式三:从源码安装(获取最新功能)
git clone https://github.com/Ishannaik/agent-sweep
cd agent-sweep
pip install -e .
# 验证安装
python -c "import agent_sweep; print('安装成功')"
# 命令行使用
agent-sweep --help
# 基本用法
agent-sweep input_file -o output_file
# Python 代码中调用
import agent_sweep
# 示例
result = agent_sweep.process("input")
print(result)
# agent-sweep 配置文件示例(config.yml) app: name: "agent-sweep" debug: false log_level: "INFO" # 运行时指定配置文件 agent-sweep --config config.yml # 或通过环境变量配置 export AGENT_SWEEP_API_KEY="your-key" export AGENT_SWEEP_OUTPUT_DIR="./output"

191 high-confidence patterns plus a checksum-validated crypto seed-phrase detector — BIP-39 mnemonics (12/15/18/21/24 words; the wallet format behind BTC, ETH, SOL, BNB, ADA, DOGE, LTC, DOT, AVAX and virtually every major chain) and Electrum seeds are confirmed cryptographically (BIP-39 checksum / Electrum version tag), so English prose that happens to use wallet words never false-positives.
The patterns: AWS access keys, GitHub tokens (PAT/OAuth/App/fine-grained), Stripe live/test, OpenAI, Anthropic, Google API, Slack bot/user/webhook, Hugging Face, JWT, PEM private keys, DB URLs with embedded passwords, npm/PyPI/SendGrid/Twilio tokens — plus 167 rules ported from the gitleaks pack covering GitLab, Grafana, HashiCorp Vault/Terraform, DigitalOcean, Shopify, PlanetScale, Databricks, Atlassian, Azure AD, 1Password, Sentry, New Relic, Mailgun, Datadog, Twilio, Twitter/X, Twitch, Yandex, JFrog, Snyk, Mailchimp, curl credentials on the command line, and many more. Patterns are high-precision — false positives are rare, and provider-context rules are keyword-gated so large pastes stay fast.
For deeper detection, run gitleaks or trufflehog alongside agentsweep — their rule packs are more exhaustive. agentsweep's value is the agent-history-specific surface, not the detection engine.
agentsweep fix --allow-production
Recommended — isolated, no venv conflicts:
uv tool install agentsweep # one-time install
uv tool upgrade agentsweep # update to latest
Try without installing (always runs latest):
uvx agentsweep@latest
Classic pip:
pip install agentsweep
pip install --upgrade agentsweep
Don't haveuv?pip install uvor see astral.sh/uv. Requires Python 3.11+.
pip install uv # get uv (skip if you already have it)
uv tool install agentsweep # install — adds `agentsweep` and `asweep` to PATH
asweep # run — interactive menu guides you through everything
That's it. No virtualenv to activate, no PATH fiddling — uv tool install gives the command its own isolated environment.
Why does uvx agentsweep show an old version? uvx caches tools locally. Use uvx agentsweep@latest to always run the newest version (recommended), or force a cache refresh with uvx --reinstall agentsweep.
Where is OpenCode in the menu? OpenCode support was added in v0.1.1. Run pip install --upgrade agentsweep or uvx agentsweep@latest to get it.
Does agentsweep send my data anywhere? No. It is fully offline — zero network calls during scanning or redacting. The only optional network call is the background update check, which only fetches the latest version number from PyPI.
agent-sweep是一个开源的AI工作流,帮助开发者发现和隐藏敏感信息,提高代码安全性和透明度,值得关注。
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ MIT 协议 — 最宽松的开源协议之一,可自由商用、修改、分发,仅需保留版权声明。
经综合评估,AI工作流:敏感信息扫描 在Agent工作流赛道中表现稳健,质量良好。如果你已有明确的使用需求,可以直接上手体验;如果还在评估阶段,建议对比同类工具后再做决策。
| 原始名称 | agent-sweep |
| 原始描述 | 开源AI工作流:Find and redact secrets in AI coding agent histories (Claude Code, and more).。⭐24 · Python |
| Topics | workflowai-agentsclaude-codeclideveloper-toolsdlppython |
| GitHub | https://github.com/Ishannaik/agent-sweep |
| License | MIT |
| 语言 | Python |
收录时间:2026-06-13 · 更新时间:2026-06-16 · License:MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端