@telora/daemon@0.22.52
Agent orchestration daemon for Telora - spawns and manages Claude Code instances
AI Security Review
scanned 1mo ago · by lpm-firewall-aiThe package is not proven malicious, but its remote-driven permission-bypassing agent execution, configuration writes, hooks, and automatic self-update create substantial unresolved risk. Its only publish lifecycle hook is prepublishOnly, so the stricter install-hook blocking rule does not apply.
Decision evidence
public snapshot- The daemon starts an automatic updater and installs its latest global package release.
- A running daemon can create or modify Claude project settings across configured repositories.
- The connect command adds executable PostToolUse and UserPromptSubmit hooks to the user's Claude settings.
- Remote intake data is supplied to a Claude process launched with permission checks disabled.
- package.json has no install, preinstall, or postinstall lifecycle hook.
- The risky configuration flow is reached through explicit connect or daemon-run commands rather than package installation.
- The inspected code contains no direct credential harvesting or secret exfiltration logic.
Source & flagged code
7 flagged · loading sourcePackage source references child process execution.
dist/update/self-update.jsView on unpkg · L25Package source invokes a package manager install command at runtime.
dist/update/self-update.jsView on unpkg · L16Findings
Affected versions and remediation
This report applies to @telora/daemon@0.22.52.
See all versions of @telora/daemon for other recorded verdicts.
- Review the evidence and your use of @telora/daemon@0.22.52 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.