@telora/daemon@0.24.2
Agent orchestration daemon for Telora - spawns and manages Claude Code instances
AI Security Review
scanned 8d ago · by lpm-firewall-aiThe package does not show an install-time attack, but its explicit connect flow automatically enables global prompt and tool hooks when the tracking CLI is present. That agent configuration capability warrants a warning; the inspected source does not establish data exfiltration.
Decision evidence
public snapshot- The CLI connect flow conditionally registers tracking when `telora-ai` is available on PATH.
- Connect adds commands to global Claude settings for prompt submission and after tool use, without a separate hook-consent step in that flow.
- The manifest’s only lifecycle script is `prepublishOnly`, which runs the build and build-info stamping.
- The hook setup runs from the explicit connect command and depends on `telora-ai` being present; the inspected source does not show the hook commands’ data transfer behavior.
Source & flagged code
7 flagged · loading sourcePackage source references child process execution.
dist/update/self-update.jsView on unpkg · L27Package source invokes a package manager install command at runtime.
dist/update/self-update.jsView on unpkg · L17Findings
Affected versions and remediation
This report applies to @telora/daemon@0.24.2.
See all versions of @telora/daemon for other recorded verdicts.
- Review the evidence and your use of @telora/daemon@0.24.2 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.