@telora/daemon@0.22.78
Agent orchestration daemon for Telora - spawns and manages Claude Code instances
AI Security Review
scanned 3d ago · by lpm-firewall-aiSource inspection found no concrete malware behavior, but confirmed automatic boot-time mutation of Claude agent settings in configured repositories. This first-party extension setup warrants a warning because it can install a session hook beyond the initial connect action.
Decision evidence
public snapshot- At daemon boot, the package refreshes Claude settings for every configured product repository.
- The refresh writes a merged `.claude/settings.json`; this can install a SessionStart hook into an existing repository.
- The connect command is an explicit setup flow that starts the daemon and configures agent integrations.
- The manifest has only a `prepublishOnly` lifecycle script, which builds and stamps package metadata.
- The Claude settings merge is idempotent and skips writes when the file is unchanged.
- The inspected Lacuna process runner installs a sidecar only when its Python environment is missing and requires a configured source.
- The inspected spawn lifecycle excerpt checks merge conflicts and records agent success or failure.
Source & flagged code
6 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@0.22.78.
See all versions of @telora/daemon for other recorded verdicts.
- Review the evidence and your use of @telora/daemon@0.22.78 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.