registry / ttj-skills-browser / 1.2.10

ttj-skills-browser@1.2.10

Renamed to 'ttj-skills-playwright'. Please install: npm i -g ttj-skills-playwright

ttj-skills-browser - Dedicated CDP browser with one-shot commands (eval/goto/screenshot) and page reference visualization

AI Security Review

scanned 2mo ago · by lpm-firewall-ai

LPM treats this as warn-only first-party agent extension lifecycle risk. Postinstall mutates global Claude Code and Codex skill directories without a separate setup command. The installed skill grants a persistent-profile browser automation capability with arbitrary page evaluation; no source-confirmed data exfiltration was found.

Static reason

High-risk behavior combination matched malicious policy.

Trigger

`npm install` triggers postinstall; invoking the CLI triggers browser launch, CDP actions, and daily update checks.

Impact

An installed agent can be instructed to access the active browser profile and execute page JavaScript; future package code is fetched by the self-update path.

Mechanism

Global AI-agent skill installation plus local CDP browser automation and runtime self-update.

Rationale

This is a first-party, package-named agent-extension setup with powerful browser-control instructions and automatic updates, not a source-confirmed exfiltration or destructive malware chain. It warrants a warning under the extension lifecycle policy rather than a publish block.

Evidence

package.jsonscripts/install-skill.js.claude/skills/ttj-skills-browser/SKILL.mddist/browser.jsdist/cdp.jsdist/utils.js~/.claude/skills/ttj-skills-browser/SKILL.md~/.agents/skills/ttj-skills-browser/SKILL.md~/.ttj-skills-browser/.last-update-check/tmp/ttj-screenshot.png/tmp/ttj-refs-visual.png

ttj-skills-browser@1.2.10

AI Security Review

Decision evidence

Source & flagged code

Source & flagged code

Findings

Source & flagged code