ClawHub

Browser Read

v1.0.0

Extract readable content from browser pages as markdown. Use when web_fetch fails (bot protection, auth-required pages, Twitter/X, LinkedIn) and you already...

⭐ 0· 154·0 current·0 all-time
by@bill492
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
Name/description (extract readable content from an open browser page) match the included JS and SKILL.md. No unrelated binaries or credentials are requested.
ℹ
Instruction Scope
Instructions tell the agent to read the extractor from ~/clawd/skills/browser-read/extract.js and run it in the browser via browser act evaluate. Reading the skill's own file and executing it in the page context is expected for this purpose; verify the runtime will only read the skill path (not arbitrary host files) and that browser evaluate is appropriately sandboxed.
✓
Install Mechanism
No install spec — instruction-only with one included JS file. Nothing is downloaded from external URLs and no archives are extracted.
✓
Credentials
No environment variables, credentials, or config paths are required. The extract script only reads DOM content, metadata, and document.location (expected for content extraction).
✓
Persistence & Privilege
Skill is not always-enabled and is user-invocable. It does not request elevated persistence or modify other skills or system-wide settings.
Assessment
This skill appears coherent and low-risk: it runs a JS extractor inside the browser page and returns markdown, and it does not request secrets or make network calls. Before installing, confirm that (1) the agent's file-access is limited to the skill directory (the SKILL.md references ~/clawd/skills/browser-read/extract.js), (2) you are comfortable allowing the agent to evaluate scripts in pages you open (the script can read page content, metadata, and URLs), and (3) you avoid running it on highly sensitive pages (banking, 2FA flows) or pages where extracting content violates terms. If you want extra assurance, review extract.js yourself and test it on a non-sensitive page first.

Like a lobster shell, security has layers — review code before you run it.

latestvk974n645yacq0nj0ywcnvm8dtx835177

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments