open-tag@0.1.1
OpenTag command-line interface for connecting team messaging with AI coding agents.
AI Security Review
scanned 19d ago · by lpm-firewall-aiThe source does not substantiate the scanner’s credential-redirection or persistent agent-control claims. The manifest has no install hook, and the inspected runtime paths align with the declared CLI and hosted-tool functionality.
Decision evidence
public snapshot- package.json points to a CLI and runtime module and defines no install lifecycle hook.
- The CLI runs when its executable is invoked; package.json lists only build, start, typecheck, and test scripts.
- The flagged agent-related code lists skill directories and prepares a Claude Code hosted-tool bridge during runtime.
- That bridge uses a temporary configuration and a loopback server for OpenTag tools.
- Authenticated API requests use the server URL saved in OpenTag credentials.
- The declaration file exposes the package’s command and result APIs.
Source & flagged code
6 flaggedThis package version adds a dangerous source file absent from the previous stored version; route for source-aware review.
dist/program-CXdTyo53.mjsView on unpkgPackage source references child process execution.
dist/program-CXdTyo53.mjsView on unpkg · L10Findings
Affected versions and remediation
This report applies to open-tag@0.1.1.
See all versions of open-tag for other recorded verdicts.
- Review the evidence and your use of open-tag@0.1.1 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.