@agimon-ai/po-browse-tool@0.0.0-alpha.56
MCP server for browser automation using Playwright with profile management, page registry, and multi-browser support
AI Security Review
scanned 8d ago · by lpm-firewall-aiThe source supports browser automation and local process management, while the flagged process output is captured locally. The manifest has no install lifecycle hook, and no concrete attack behavior was identified in the inspected dependency snapshots.
Decision evidence
public snapshot- package.json exports the reviewed CommonJS and ESM runtime entrypoints and declares no lifecycle hooks.
- The runtime entrypoints import browser automation and local package modules; the inspected command-output capture collects stdout and stderr from a launched browser process.
- The three inspected dependency manifests declare no lifecycle scripts, and their entrypoints expose port-registry, process-registry, and validation functionality.
- The inspected dependency entrypoints contain module exports or schema utilities; no attack behavior was identified in these snapshots.
- The scanner flagged shell execution and command-output exfiltration, but the inspected process calls are used for process discovery and browser launch, and captured output is collected locally.
- The package manifest contains build and development scripts, with no preinstall, install, or postinstall hook.
Source & flagged code
9 flaggedThis package version adds a dangerous source file absent from the previous stored version; route for source-aware review.
dist/index.cjsView on unpkgFindings
Affected versions and remediation
This report applies to @agimon-ai/po-browse-tool@0.0.0-alpha.56.
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@0.0.0-alpha.56 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.