registry  /  ttj-skills-playwright  /  1.4.10

ttj-skills-playwright@1.4.10

Drive an existing Chrome over CDP (Playwright core) with one-shot commands — eval, goto, click, type, wait, tabs, screenshot — plus page element visualization and crawl-target analysis. Skill for Claude Code & Codex.

AI Security Review

scanned 3h ago · by lpm-firewall-ai

LPM blocks this version under the AI-agent control-surface policy. npm postinstall silently installs package-controlled agent instructions into global Claude Code and Codex skill directories. The installed skill can auto-invoke and directs agents to use its browser-control CLI.

Static reason
High-risk behavior combination matched malicious policy.; source matched previously finalized malicious package; routed for review; previous stored version diff introduced dangerous source
Trigger
`npm install` or global installation executes `postinstall`.
Impact
Unconsented persistent agent behavior and tool-use guidance is added for future Claude Code/Codex sessions.
Mechanism
Postinstall writes package-supplied AI-agent skill files into global agent control surfaces.
Policy narrative
Installing the package executes `scripts/install-skill.js`, which copies a package-controlled skill into global Claude Code and Codex agent directories and creates an installation marker. The installed skill declares broad auto-invocation patterns and Bash/Read/Write permissions, making future agent behavior depend on unconsented package-supplied instructions. Its browser automation functions are user-facing, but they do not remove the install-time agent-control-surface mutation.
Rationale
The concrete postinstall mutation of global third-party AI-agent skill directories meets the block boundary. No separate exfiltration chain is needed for this verdict.
Evidence
package.jsonscripts/install-skill.js.claude/skills/ttj-skills-playwright/SKILL.mddist/utils.jsdist/browser.js~/.claude/skills/ttj-skills-playwright/SKILL.md~/.agents/skills/ttj-skills-playwright/SKILL.md~/.ttj-skills-playwright-installed
Network endpoints1
registry.npmjs.org/ttj-skills-playwright/latest

Decision evidence

public snapshot
AI called this Malicious at 98.0% confidence as Malware with low false-positive risk.
Evidence for policy block
  • `package.json` runs `postinstall` on npm installation.
  • `scripts/install-skill.js` copies package `SKILL.md` into `~/.claude/skills/ttj-skills-playwright/`.
  • `scripts/install-skill.js` writes a converted skill into `~/.agents/skills/ttj-skills-playwright/`.
  • `.claude/skills/ttj-skills-playwright/SKILL.md` enables broad auto-invocation and permits Bash, Read, and Write.
  • The lifecycle script creates `~/.ttj-skills-playwright-installed` without user interaction.
Evidence against
  • No credential harvesting or external data-exfiltration code was found.
  • The only package network endpoint inspected is npm registry version checking.
  • Browser/CDP automation is exposed as explicit CLI functionality, not an install-time payload.
Behavioral surface
Source
ChildProcessEnvironmentVarsFilesystemNetworkShell
Supply chain
HighEntropyStringsUrlStrings
ManifestNo manifest risk signals triggered.
scanned 10 file(s), 87.3 KB of source, external domains: 127.0.0.1, example.com, registry.npmjs.org, www.google.com, www.naver.com

Source & flagged code

6 flagged · loading source
package.jsonView file
scripts.postinstall = node scripts/install-skill.js
High
Install Time Lifecycle Scripts

Package defines install-time lifecycle scripts.

package.jsonView on unpkg
dist/utils.jsView file
5import path from 'path'; L6: import net from 'net'; L7: import http from 'http'; L8: import https from 'https'; L9: import { exec } from 'child_process'; L10: import { promisify } from 'util'; ... L18: */ L19: export const getOsType = () => process.platform === 'win32' L20: ? 'windows' ... L26: */ L27: export const getHomeDir = () => os.homedir(); L28: /**
High
Sandbox Evasion Gated Capability

Source gates dangerous network, credential, or execution behavior behind CI, host, platform, time, or geo fingerprint checks.

dist/utils.jsView on unpkg · L5
matchType = normalized_sha256 matchedPackage = ttj-sk[redacted]@1.4.9 matchedPath = dist/utils.js matchedIdentity = npm:dHRqLXNraWxscy1wbGF5d3JpZ2h0:1.4.9 similarity = 1.000 summary = normalized source hash matched finalized malicious source
High
Known Malware Source Similarity

Source file is highly similar to a previously finalized malicious package; route for source-aware review.

dist/utils.jsView on unpkg
scripts/install-skill.jsView file
14Install-time AI-agent control hijack evidence: L14: const skillName = 'ttj-sk[redacted]'; L15: const sk[redacted] = path.join(__dirname, '..', '.claude', 'skills', skillName); L16: const skillFile = 'SKILL.md'; ... L19: if (!fs.existsSync(dir)) { L20: fs.mkdirSync(dir, { recursive: true }); L21: } ... L53: // Claude Code: 기존 /ttj-sk[redacted] 호출 방식 유지 L54: const claudeTargetDir = path.join(homedir(), '.claude', 'skills', skillName); L55: const claudeTargetFile = path.join(claudeTargetDir, skillFile); L56: ensureDir(claudeTargetDir); L57: fs.copyFileSync(sourceFile, claudeTargetFile); L58: console.log(`✅ Claude Code 스킬 설치 완료: ${claudeTargetFile}`); Payload evidence from .claude/skills/ttj-sk[redacted]/SKILL.md: L40: L41: When the skill is activated, always start with the bare command `ttj-sk[redacted]` (no subcommand). It checks the dedicated ttj profile browser on CDP port 9227 (probing the p... L42: ... L135: ```bash L136: ttj-sk[redacted] goto https://example.com L137: ttj-sk[redacted] goto example.com # https:// auto-prefixed
Critical
Ai Agent Control Hijack

Install-time source drops package-supplied AI-agent/MCP control files or instructions.

scripts/install-skill.jsView on unpkg · L14
dist/cli.jsView file
matchType = normalized_sha256 matchedPackage = ttj-sk[redacted]@1.4.9 matchedPath = dist/cli.js matchedIdentity = npm:dHRqLXNraWxscy1wbGF5d3JpZ2h0:1.4.9 similarity = 1.000 summary = normalized source hash matched finalized malicious source
High
Known Malware Source Similarity

Source file is highly similar to a previously finalized malicious package; route for source-aware review.

dist/cli.jsView on unpkg
dist/browser.jsView file
matchType = previous_version_dangerous_delta matchedPackage = ttj-sk[redacted]@1.4.6 matchedIdentity = npm:dHRqLXNraWxscy1wbGF5d3JpZ2h0:1.4.6 similarity = 0.500 summary = stored previous version shares package body but lacks this dangerous source file
High
Previous Version Dangerous Delta

This package version adds a dangerous source file absent from the previous stored version; route for source-aware review.

dist/browser.jsView on unpkg

Findings

1 Critical5 High3 Medium5 Low
CriticalAi Agent Control Hijackscripts/install-skill.js
HighInstall Time Lifecycle Scriptspackage.json
HighSandbox Evasion Gated Capabilitydist/utils.js
HighKnown Malware Source Similaritydist/utils.js
HighKnown Malware Source Similaritydist/cli.js
HighPrevious Version Dangerous Deltadist/browser.js
MediumNetwork
MediumEnvironment Vars
MediumStructural Risk Force Deep Review
LowNon Install Lifecycle Scripts
LowScripts Present
LowFilesystem
LowHigh Entropy Strings
LowUrl Strings