@telora/daemon@0.22.169
Agent orchestration daemon for Telora - spawns and manages Claude Code instances
AI Security Review
scanned 15d ago · by lpm-firewall-aiThe source shows an explicit connect flow modifying Codex and Claude agent configuration, a concrete agent capability that merits a warning. The manifest declares only prepublishOnly, so the inspected evidence does not show unconsented install-time mutation or a confirmed malicious chain.
Decision evidence
public snapshot- Running the explicit connect flow writes daemon configuration and registers the Telora integration for the selected harness.
- The connect integration can write or merge Codex AGENTS.md instructions, including the operator-wide ~/.codex/AGENTS.md file.
- The Claude integration can merge permissions and a SessionStart hook into the repository's .claude/settings.json.
- The manifest has only a prepublishOnly script, which builds and stamps package metadata; no install lifecycle hook is declared.
- The Codex and Claude configuration changes are in the connect flow, rather than an npm install hook.
- The inspected manifest has no runtime self-dependency on @telora/daemon.
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@0.22.169.
See all versions of @telora/daemon for other recorded verdicts.
- Review the evidence and your use of @telora/daemon@0.22.169 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.