registry / @agimon-ai/po-browse-tool / 0.30.14-alpha.4
@agimon-ai/po-browse-tool@0.30.14-alpha.4
MCP server for browser automation using Playwright with profile management, page registry, and multi-browser support
AI Security Review
scanned 19d ago · by lpm-firewall-aiThe manifest has no install hook, and the inspected command, dynamic import, and network request have package-related functions. The scanner hints do not establish malicious behavior.
Static reason
One or more suspicious static signals were detected.; previous stored version diff introduced dangerous source
Trigger
A user invokes browser tooling or configures and runs a local TypeScript snippet.
Impact
No unintended credential transfer, remote payload execution, or unrelated system mutation was established.
Mechanism
The package dispatches browser operations, downloads Chrome for Testing metadata, and dynamically loads snippets from a configured directory.
AI rationale
The manifest has no install hook, and the inspected command, dynamic import, and network request have package-related functions. The scanner hints do not establish malicious behavior.
Decision evidence
public snapshotAI called this Clean at 91.0% confidence as Benign with low false-positive risk.
Evidence for AI clean decision
- package.json defines no install lifecycle hooks; its scripts are development and build commands.
- The CommonJS and ESM entrypoints dispatch browser operations through the package’s browser tool handler.
- Chrome for Testing metadata is fetched from the Google Chrome Labs endpoint for the browser installer.
- The package loads TypeScript snippets from a configured snippets directory; this is user-configured runtime code execution.
- The flagged child process runs Git in a supplied working directory to resolve local repository metadata.
Evidence against
- The flagged command output is used to resolve a local Git directory; the inspected code does not send it over the network.
- The dynamic import loads configured local snippets, and the inspected network request serves Chrome for Testing setup.
Behavioral surface
ChildProcessCryptoDynamicRequireEnvironmentVarsEvalFilesystemNetworkShell
Source & flagged code
7 flaggeddist/dockerChromeForTesting-BMmEQq88.mjsView file
1import{t as e}from"./decorateMetadata-D0fK5b4i.mjs";import{t}from"./decorate-B3KLIx2E.mjs";import"reflect-metadata/lite";import{injectable as n}from"inversify";import r,{join as i}...
L2: //# sourceMappingURL=dockerChromeForTesting-BMmEQq88.mjs.map
High
Child Process
Package source references child process execution.
dist/dockerChromeForTesting-BMmEQq88.mjsView on unpkg · L11import{t as e}from"./decorateMetadata-D0fK5b4i.mjs";import{t}from"./decorate-B3KLIx2E.mjs";import"reflect-metadata/lite";import{injectable as n}from"inversify";import r,{join as i}...
L2: //# sourceMappingURL=dockerChromeForTesting-BMmEQq88.mjs.map
High
Same File Env Network Execution
A single source file combines environment access, network access, and code or shell execution; review context before blocking.
dist/dockerChromeForTesting-BMmEQq88.mjsView on unpkg · L1dist/extension/background.jsView file
Findings
1 Critical5 High4 Medium5 Low
CriticalPrevious Version Dangerous Deltadist/container-DrE51Rho.cjs
HighChild Processdist/dockerChromeForTesting-BMmEQq88.mjs
HighShell
HighSame File Env Network Executiondist/dockerChromeForTesting-BMmEQq88.mjs
HighCommand Output Exfiltrationdist/container-D-D4x8I7.mjs
HighTrigger Reachable Command Output Exfiltrationdist/container-DrE51Rho.cjs
MediumDynamic Requiredist/stubs/playwright-test.cjs
MediumNetwork
MediumEnvironment Vars
MediumStructural Risk Force Deep Review
LowScripts Present
LowEvaldist/extension/background.js
LowFilesystem
Affected versions and remediation
This report applies to @agimon-ai/po-browse-tool@0.30.14-alpha.4.
See all versions of @agimon-ai/po-browse-tool for other recorded verdicts.
- Review the evidence and your use of @agimon-ai/po-browse-tool@0.30.14-alpha.4 before allowing it. Restrict the permissions described in this report.
- Choose an independently verified alternative or release. This report does not establish that other versions are safe.
Evidence last updated: .
Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.