@telora/daemon@0.22.0
Agent orchestration daemon for Telora - spawns and manages Claude Code instances
AI Security Review
scanned 1mo ago · by lpm-firewall-aiThis package presents a real agent-extension and self-update capability that warrants a warning. The source does not establish malicious install-time behavior, credential theft, or an opaque lifecycle self-dependency chain.
Decision evidence
public snapshot- The explicit connect command can add Telora instructions and an MCP server to the operator's global Codex control files.
- When a separate telora-ai binary is already on PATH, connect adds command hooks to the user's Claude settings.
- The running daemon can automatically run a global npm install of a newer package version.
- package.json has only a prepublishOnly lifecycle hook; registry installation does not execute package code.
- The agent-control writes are reached through the user-invoked connect command, not an install hook.
- The inspected network request redeems the token supplied to connect; no source-confirmed credential harvesting or secret exfiltration was found.
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@0.22.0.
See all versions of @telora/daemon for other recorded verdicts.
- Review the evidence and your use of @telora/daemon@0.22.0 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.