@telora/daemon@0.22.187
Agent orchestration daemon for Telora - spawns and manages Claude Code instances
AI Security Review
scanned 15d ago · by lpm-firewall-aiThe source supports a warning for explicit first-party agent setup through the connect flow, which writes agent configuration. It does not establish an install-hook attack, credential exfiltration, or other concrete malicious behavior.
Decision evidence
public snapshot- The manifest has a `prepublishOnly` build script and no registry install hook; the flagged setup is not triggered by npm installation.
- The exported connection flow is a CLI operation that writes daemon configuration under the user’s Telora directory.
- The connection flow includes a Codex instructions-file writer, and Claude configuration supports merging a session-start hook.
- The Cline integration reads Telora identity from the daemon configuration; its cited code describes integration wiring.
- Source inspection did not establish exfiltration, destructive behavior, or an install-time agent configuration change.
- The cited setup is exposed through the explicit connect command and config-writing functions.
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@0.22.187.
See all versions of @telora/daemon for other recorded verdicts.
- Review the evidence and your use of @telora/daemon@0.22.187 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.