技能 extract
📦

extract

内容修订 r1 高风险 ⚙️ 外部命令🌐 网络访问📁 文件系统访问🔑 环境变量

使用 Tavily 提取干净的网页内容

当页面包含导航、脚本和格式噪音时，干净的网页内容很难收集。此技能通过 Tavily 从已知 URL 中提取可读的 markdown 或文本。

支持: Claude Codex Code(CC)
⚠️ 38 差

使用我的智能体安装

将此请求复制给你的智能体，其中包含权威 Skill 页面和清单。

智能体请求
Review the Skillstore skill "extract" from https://skillstore.io/skills/tavily-ai-extract.md and its manifest at https://skillstore.io/api/skills/tavily-ai-extract/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.

你的智能体仍应展示其计划，并按安全策略请求必要确认。

Agent 可读资源

当 AI Agent、爬虫或脚本需要干净上下文，而不是读取完整页面时，请使用这些链接。

Markdown 详情 GET /skills/tavily-ai-extract.md 已签名 manifest GET /api/skills/tavily-ai-extract/manifest 已签名 lockfile GET /api/skills/tavily-ai-extract/lockfile

测试它

正在使用“extract”。 提取关于身份验证的文档页面。

预期结果:

包含标题、章节、示例和原始源 URL 的可读 markdown 页面。

正在使用“extract”。 提取五个产品页面，并聚焦价格详情。

预期结果:

按来源组织的总结，包含相关价格文本、提取的页面内容以及任何失败的 URL。

正在使用“extract”。 提取带图片的 JavaScript 密集型仪表板页面。

预期结果:

高级提取结果，包含可见文本、可用图片 URL，以及关于缺失内容的说明。

安全审计

高风险
v4 • 2026/7/7 打开版本化报告

The skill performs a legitimate Tavily extraction workflow through an included shell script. Confirmed risks are OAuth token cache reads, environment secret handling, bearer token transmission, and unpinned npx execution. Most Markdown backtick, example URL, and /dev/null findings are false positives, and I found no prompt injection text.

2
已扫描文件
369
分析行数
18
复核项
0
已忽略误报

已确认安全问题 (1)

高
scripts/extract.sh:98
Unpinned Package Execution During OAuth
scripts/extract.sh runs npx -y mcp-remote when no token is found. The package version is not pinned, so authentication can execute newly published npm code.
The command directly invokes npx with automatic yes behavior on a package name and no version pin. This is a clear supply-chain execution risk during normal authentication.
能力复核项 (18)

这些是真实的本地能力，对此技能可能是预期行为，因此需要复核，但不会按已确认恶意行为计分。

高
scripts/extract.sh:50
Shell command substitution
token=$(jq -r '.access_token // empty' "$token_file" 2>/dev/null)
The command substitution reads access_token values from token cache files. Those credentials are later exported and used for Tavily authentication.
高
scripts/extract.sh:67
Shell command substitution
token=$(get_mcp_token) || true
This command substitution invokes get_mcp_token, which searches the local MCP auth cache for bearer tokens. It is intended behavior, but it is credential discovery.
高
scripts/extract.sh:107
Shell command substitution
token=$(get_mcp_token) || true
This command substitution repeats token cache discovery during OAuth polling. It can load a local bearer token into the skill process.
高
scripts/extract.sh:151-157
Shell command substitution
RESPONSE=$(curl -s --request POST \
The command substitution executes curl and captures a response from the Tavily MCP endpoint. It sends user-provided extraction arguments and an Authorization header to a third party.
高
scripts/extract.sh:98
Hardcoded URL
npx -y mcp-remote https://mcp.tavily.com/mcp </dev/null >/dev/null 2>&1 &
The hardcoded Tavily MCP URL is used by the OAuth helper during authentication. This creates live third-party network access before extraction runs.
高
scripts/extract.sh:152
Hardcoded URL
--url "https://mcp.tavily.com/mcp" \
The script posts extraction requests to the hardcoded Tavily MCP endpoint. It sends requested URLs, options, and a bearer token outside the local environment.
高
scripts/extract.sh:45
Hidden file access
MCP_AUTH_DIR="$HOME/.mcp-auth"
The script explicitly targets $HOME/.mcp-auth, a hidden auth cache under the user home directory. Reading this directory can expose stored OAuth tokens.
高
scripts/extract.sh:50
Standard device file access
token=$(jq -r '.access_token // empty' "$token_file" 2>/dev/null)
The jq command reads access_token from token files discovered under the MCP auth cache. This is real credential file access, not only device redirection.
高
scripts/extract.sh:60
Standard device file access
done < <(find "$MCP_AUTH_DIR" -name "*_tokens.json" 2>/dev/null)
The find command recursively scans the hidden MCP auth directory for token files. This broad search can discover local credentials available to the process.
高
scripts/extract.sh:66
Generic API/secret keys
if [ -z "$TAVILY_API_KEY" ]; then
The script checks the TAVILY_API_KEY environment variable as part of authentication flow. This is intended, but it is real access to a secret-bearing environment value.
高
scripts/extract.sh:69
Generic API/secret keys
export TAVILY_API_KEY="$token"
The script exports a discovered OAuth token as TAVILY_API_KEY. This places a bearer credential into the process environment for later network use.
高
scripts/extract.sh:94
Generic API/secret keys
if [ -z "$TAVILY_API_KEY" ]; then
The script checks the TAVILY_API_KEY environment variable as part of authentication flow. This is intended, but it is real access to a secret-bearing environment value.
高
scripts/extract.sh:109
Generic API/secret keys
export TAVILY_API_KEY="$token"
The script exports a discovered OAuth token as TAVILY_API_KEY. This places a bearer credential into the process environment for later network use.
高
scripts/extract.sh:120
Generic API/secret keys
if [ -z "$TAVILY_API_KEY" ]; then
The script checks the TAVILY_API_KEY environment variable as part of authentication flow. This is intended, but it is real access to a secret-bearing environment value.
高
scripts/extract.sh:153
Generic API/secret keys
--header "Authorization: Bearer $TAVILY_API_KEY" \
The Authorization header sends TAVILY_API_KEY as a bearer token to Tavily. This is intended API authentication, but it is confirmed secret transmission.
高
SKILL.md:13
Hidden file in home directory
1. Check for existing tokens in `~/.mcp-auth/`
The documentation states that the skill checks ~/.mcp-auth for existing tokens. This documents hidden home-directory credential access that the script also performs.
高
SKILL.md:13
Hidden file access
1. Check for existing tokens in `~/.mcp-auth/`
The documentation states that the skill checks ~/.mcp-auth for existing tokens. This documents hidden home-directory credential access that the script also performs.
中
scripts/extract.sh:1
Unix shell invocation
#!/bin/bash
The skill ships an executable shell script that runs local commands, network tools, and auth-token discovery. Script execution is intended, but it expands the skill trust boundary.

风险因素

⚙️ 外部命令 (52)
scripts/extract.sh:11 scripts/extract.sh:13 scripts/extract.sh:23 scripts/extract.sh:26 scripts/extract.sh:32 scripts/extract.sh:34 scripts/extract.sh:50 scripts/extract.sh:67 scripts/extract.sh:105 scripts/extract.sh:107 scripts/extract.sh:140-148 scripts/extract.sh:151-157 scripts/extract.sh:160 scripts/extract.sh:1 SKILL.md:13 SKILL.md:20 SKILL.md:21-27 SKILL.md:27-33 SKILL.md:33-35 SKILL.md:35-38 SKILL.md:38-50 SKILL.md:50-54 SKILL.md:54-62 SKILL.md:62-66 SKILL.md:66-79 SKILL.md:79-85 SKILL.md:85-87 SKILL.md:87-93 SKILL.md:93 SKILL.md:94 SKILL.md:100-101 SKILL.md:101-102 SKILL.md:102-103 SKILL.md:103 SKILL.md:104 SKILL.md:105-106 SKILL.md:106-110 SKILL.md:110-121 SKILL.md:121-127 SKILL.md:127-128 SKILL.md:128-134 SKILL.md:134-143 SKILL.md:143-147 SKILL.md:147-160 SKILL.md:160-164 SKILL.md:164-174 SKILL.md:174-178 SKILL.md:178-193 SKILL.md:193-198 SKILL.md:198 SKILL.md:199 SKILL.md:200-201
🌐 网络访问 (32)
scripts/extract.sh:4 scripts/extract.sh:27 scripts/extract.sh:89 scripts/extract.sh:98 scripts/extract.sh:123 scripts/extract.sh:152 SKILL.md:16 SKILL.md:20 SKILL.md:40 SKILL.md:43 SKILL.md:46 SKILL.md:49 SKILL.md:56 SKILL.md:60 SKILL.md:68 SKILL.md:73 SKILL.md:74 SKILL.md:86 SKILL.md:114 SKILL.md:136 SKILL.md:140 SKILL.md:149 SKILL.md:154 SKILL.md:155 SKILL.md:166 SKILL.md:170 SKILL.md:180 SKILL.md:185 SKILL.md:186 SKILL.md:187 SKILL.md:188 SKILL.md:189
📁 文件系统访问 (16)
scripts/extract.sh:45 scripts/extract.sh:17 scripts/extract.sh:26 scripts/extract.sh:32 scripts/extract.sh:50 scripts/extract.sh:60 scripts/extract.sh:98 scripts/extract.sh:115 scripts/extract.sh:116 scripts/extract.sh:128 scripts/extract.sh:134 scripts/extract.sh:163 SKILL.md:13 SKILL.md:20 SKILL.md:13 SKILL.md:20
🔑 环境变量 (16)
scripts/extract.sh:65 scripts/extract.sh:66 scripts/extract.sh:69 scripts/extract.sh:94 scripts/extract.sh:109 scripts/extract.sh:120 scripts/extract.sh:123 scripts/extract.sh:153 SKILL.md:24 SKILL.md:57 SKILL.md:69 SKILL.md:93 SKILL.md:137 SKILL.md:150 SKILL.md:167 SKILL.md:181
审计者: codex 查看审计历史 →
分享与引用此报告

分享版本化评估报告、中性徽章、嵌入卡片和引用。Skillstore 只报告证据，不判断该 Skill 是否安全。

打开版本化报告
安全评估

复制报告链接

https://skillstore.io/skills/tavily-ai-extract/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown 徽章

[![Skillstore security assessment](https://skillstore.io/badges/skills/tavily-ai-extract/security.svg)](https://skillstore.io/skills/tavily-ai-extract?utm_source=security_passport_badge)

HTML 徽章

<a href="https://skillstore.io/skills/tavily-ai-extract?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/tavily-ai-extract/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

嵌入卡片

<iframe src="https://skillstore.io/embed/skills/tavily-ai-extract.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>
学术引用 (APA · BibTeX · CFF)

APA 引用

tavily-ai. (2026). extract security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/tavily-ai-extract/audits/4

BibTeX 引用

@techreport{tavily-ai-tavily-ai-extract-2026, author = {tavily-ai}, title = {extract security audit report (audit version 4)}, institution = {Skillstore}, year = {2026}, number = {4}, url = {https://skillstore.io/skills/tavily-ai-extract/audits/4}, note = {Author version unspecified} }

CITATION.cff

cff-version: 1.2.0 message: "If you use this Skill, cite its author and this versioned security audit report." title: "extract security audit report (audit version 4)" version: "unspecified" type: report authors: - name: "tavily-ai" date-released: "2026-07-07" url: "https://skillstore.io/skills/tavily-ai-extract/audits/4" identifiers: - type: other value: "skillstore:tavily-ai-extract:audit:4" description: "Skillstore immutable audit report identifier"

比较变体

3 个可安装变体

每位作者的技能都保持为独立的可安装项。推荐变体按 Skillstore 证据排序。

为什么此变体排名第一

Skillstore 评分最高
pbakaus 推荐

pbakaus-extract

Skillstore 评分 79
证据置信度 高
Skillstore 使用量 15
已更新

2026-09-09

tavily-ai 当前

tavily-ai-extract

Skillstore 评分 38
证据置信度 中
Skillstore 使用量 12
已更新

2026-09-09

actionbook

actionbook-extract

Skillstore 评分 38
证据置信度 中
Skillstore 使用量 3
已更新

2026-09-09

Skillstore 评分

评分依据 证据置信度: 中
45
架构
85
可维护性
85
内容
71
社区
91
规范符合性

你能构建什么

收集研究来源

在总结或比较已知文章之前，提取其中的可读内容。

审查文档页面

从 API 文档中提取干净的章节，用于实现规划或支持回答。

监控公开页面

从公开产品页面中提取内容，用于审计、比较和更新跟踪。

试试这些提示

提取单个页面 
使用 extract 技能从此 URL 提取 markdown：[URL]。返回标题、要点和源 URL。
提取多个来源 
从这些 URL 中提取内容：[URL list]。按每个来源返回一个章节，并注明任何失败的页面。
按主题聚焦 
使用查询聚焦提取这些文档页面：[topic]。仅保留最相关的内容块，并引用每个源 URL。
使用高级提取 
对这些 JavaScript 密集型页面使用高级提取。在可用时包含图片 URL，并总结缺失或失败的内容。

最佳实践

  • 仅提取允许你与 Tavily 共享的 URL。
  • 当你需要从长页面中获取特定章节时，使用查询聚焦。
  • 先从基础提取开始，然后对缺失内容使用高级模式。

避免

  • 未经批准，不要发送私有、付费或机密 URL。
  • 未经来源审查，不要将提取的内容视为已验证事实。
  • 不要批量处理超过 API 限制支持数量的 URL。

常见问题

此技能需要 Tavily 账户吗？
是的。你需要现有的 Tavily 账户，以及有效的 OAuth 令牌或 API 密钥。
它会搜索网页吗？
不。它会从你已提供的 URL 中提取内容。
哪些数据会发送给 Tavily？
请求的 URL、提取选项和身份验证令牌会发送给 Tavily。
它能处理 JavaScript 渲染的页面吗？
可以。对于基础提取遗漏内容的页面，请使用高级提取。
身份验证来自哪里？
脚本会读取 MCP 身份验证缓存，或使用 TAVILY_API_KEY 环境变量。
它对私有页面安全吗？
仅在你的策略允许与 Tavily 共享这些 URL 和页面数据时使用它。

开发者详情

作者

tavily-ai

许可证

MIT

Skillstore 修订

r1

版本提示

作者未声明版本。

仓库

https://github.com/tavily-ai/skills/tree/main/skills/tavily/extract/

引用

36e07d5e13068e5be64447e8f20b427cf2cbd21a

维护新鲜度

2026/7/18

使用量

6 次下载 · 248 次浏览

文件结构

📁 scripts/

📄 extract.sh

📄 SKILL.md

tavily-ai 的更多技能

查看全部

相关技能

查看全部