thalamus@1.5.85
⚠ Under reviewMobile and Web client for Claude Code
AI Security Review
scanned 19d ago · by lpm-firewall-aiInspected source supports ordinary unpacking and local project-metric behavior, and the optional log path is explicitly gated and loopback-limited. The executable archive and substantial bundle behavior remain unresolved, so source inspection does not support either a clean verdict or a confirmed attack.
Decision evidence
public snapshot- The postinstall hook runs a bundled tool unpacker; its source selects platform archives and unpacks them into the package tools directory.
- The flagged API locations derive Claude project-data paths or read those project logs to compute local friction metrics.
- The MCP bin launches the package’s local bridge.
- Optional remote log shipping requires an explicit environment opt-in and restricts the configured server to loopback.
- The shipped Linux arm64 archive is executable, but its contents could not be resolved from inspected source.
- The main flagged bundles are large and were inspected only at the required agent-related locations; their remaining behavior is unresolved.
Source & flagged code
20 flaggedPackage defines install-time lifecycle scripts.
package.jsonView on unpkgPackage source references child process execution.
bin/thalamus-mcp.mjsView on unpkg · L2Findings
Affected versions and remediation
This report applies to thalamus@1.5.85.
See all versions of thalamus for other recorded verdicts.
- Review the evidence and your use of thalamus@1.5.85 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.