OpenAgentSkill
GitHub200+

Skill 审计报告

browser-use-to-stagehand 审计报告.

Migrate browser-use (Python) browser-automation scripts to Stagehand v3 (TypeScript) on Browserbase. Use when the user wants to convert, port, rewrite, or migrate a browser-use Agent script to Stagehand, map browser-use features/APIs to Stagehand primitives (act/extract/observe/agent), or move agentic browser automation onto Browserbase with more determinism. Triggers on "browser-use", "browser_use", or "Agent(task=...)".

已阻止 · 阻止需审查生成于 2026年10月14日启发式元数据审计
77
审计
67
信任
80
质量
70
安全性
88
维护
92
安装

OpenAgentSkill 信任评分

67
人工审查

OpenAgentSkill 信任评分

Trust Score 帮助 Agent 在安装前判断一个 Skill 是否足以进入候选清单。

GitHub 采用度

通过

86

3.7K 个 GitHub Stars

Star/Fork 活跃度

信息

77

3.7K 个 Star，237 个 Fork; 当前元数据中没有议题活跃度信息

近期维护

通过

88

距上次推送 1 个月

许可证清晰度

通过

86

MIT

README/SKILL.md 完整度

通过

86

元数据包含足够的用法与工作流上下文

依赖与运行时风险

失败

38

command execution surface, credential or environment access

安装可用性

通过

92

npx skills add browserbase/skills --skill browser-use-to-stagehand

安装命令安全性

通过

92

标准软件包或运行时安装路径

权限范围

失败

18

secrets or environment access, shell or command execution

仓库证据

通过

86

https://github.com/browserbase/skills/tree/main/skills/browser-use-to-stagehand

审查状态

信息

66

可用 AI 审查数据

Agent 验证结果

信息

54

暂未有 Agent 结果数据

检查项

安装与采用审查

7 通过 · 15 需审查

安装路径

92

通过

npx skills add browserbase/skills --skill browser-use-to-stagehand

仓库

88

通过

https://github.com/browserbase/skills/tree/main/skills/browser-use-to-stagehand

许可证

86

通过

MIT

维护

88

通过

距上次推送 1 个月

AI 审查

55

检查

The skill relies on external API keys and generates code that interacts with live websites; users must handle secrets responsibly, but this is inherent to the domain and not a flaw in the skill itself.

README/SKILL.md 完整度

86

通过

Usable description available

依赖风险

38

修复

command execution surface, credential or environment access

安装命令安全性

92

通过

标准软件包或运行时安装路径

权限范围

18

修复

secrets or environment access, shell or command execution

Star/Fork 活跃度

77

检查

3.7K 个 Star，237 个 Fork; 当前元数据中没有议题活跃度信息

采用度

88

通过

3.7K 个 GitHub Stars

Financial decision safety

58

检查

Research-only use: do not treat output as financial advice or execute a position without human approval.

警告

  • Dependency or permission surface needs review
  • Permission surface may require sandboxing
  • Financial research output is not financial advice; require human review before any live investment decision
  • The skill relies on external API keys and generates code that interacts with live websites; users must handle secrets responsibly, but this is inherent to the domain and not a flaw in the skill itself.
  • The skill is a point-in-time snapshot and explicitly warns that API signatures may drift; users must verify against live docs, which is a minor usability friction but correctly documented.
  • Financial research output is not financial advice; require human review before any live investment decision.
  • Quality score needs review
  • Permission surface needs review: secrets or environment access, shell or command execution
  • Dependency/runtime risk: command execution surface, credential or environment access
  • Permission surface: secrets or environment access, shell or command execution

方法

本报告综合公开元数据、AI 审查输出、仓库活跃度、安装就绪度、OpenAgentSkill 事件、质量评分、信任检查和 Agent 安全门槛；它不是完整的源代码安全审计。

对比相近选项

下一步可审计的相关 Skill

stop-slop

Eliminates predictable AI writing patterns from prose while preserving specific meaning and reader trust.

16K Stars · 审计报告

unslop

Applies Cursor's prose-discipline rules to remove filler and AI writing tells from agent-facing and user-facing text.

4.8K Stars · 审计报告

Humanizer

Rewrites AI-sounding text so it reads naturally while preserving every factual claim and matching the writer's voice.

37K Stars · 审计报告