@telora/daemon@0.22.87
Agent orchestration daemon for Telora - spawns and manages Claude Code instances
AI Security Review
scanned 1mo ago · by lpm-firewall-aiThe package intentionally provisions and operates autonomous coding agents with broad project authority and a runtime self-update path. These are real lifecycle risks, but the source does not establish concrete malicious behavior in this release.
Decision evidence
public snapshot- The running daemon refreshes an existing global Codex instruction file and configured repositories' AGENTS.md files at boot.
- It creates a worktree-local Codex configuration that disables approval prompts and permits workspace writes.
- Its auto-update loop installs the latest package globally during daemon runtime.
- The connect command sends a user-supplied connection token to the configured Telora endpoint and can start the daemon in the background.
- package.json has no preinstall, install, or postinstall lifecycle hook.
- The package does not depend on its own package name.
- The network connection and setup actions are reached through explicit CLI setup commands; no secret harvesting or unrelated 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@0.22.87.
See all versions of @telora/daemon for other recorded verdicts.
- Review the evidence and your use of @telora/daemon@0.22.87 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.