md-redline@0.10.1
Inline review comments for markdown specs. Built-in MCP server hands feedback directly to your AI agent.
AI Security Review
scanned 16d ago · by lpm-firewall-aiThe source documents a deliberate gap in static inspection, but the reviewed code does not prove an active attack. Classify as suspicious and warn while treating the threat type as unresolved.
Decision evidence
public snapshot- The launcher says its main CLI was invisible to repository static checks.
- The published launcher imports that CLI directly.
- The manifest has a prepublishOnly build script, not an install hook.
- Claude configuration changes are dispatched only by the explicit mcp install command.
- Inspected CLI network requests use loopback addresses; no credential transfer or remote payload behavior was found in the reviewed paths.
Source & flagged code
13 flaggedPackage source references child process execution.
bin/server-control.jsView on unpkg · L1This package version adds a dangerous source file absent from the previous stored version; route for source-aware review.
bin/cli.jsView on unpkgFindings
Affected versions and remediation
This report applies to md-redline@0.10.1.
See all versions of md-redline for other recorded verdicts.
- Review the evidence and your use of md-redline@0.10.1 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.