@telora/daemon@0.23.48
Agent orchestration daemon for Telora - spawns and manages Claude Code instances
AI Security Review
scanned 3d ago · by lpm-firewall-aiThe shared Codex instruction seed can affect sessions beyond the project where setup was run, so it presents a concrete agent-configuration capability. The reviewed runtime operations do not establish a separate attack, and the configuration write occurs through explicit setup, supporting a warning rather than a block.
Decision evidence
public snapshot- Explicit Codex connect setup writes a Telora instruction seed to the operator-wide ~/.codex/AGENTS.md, which is read by interactive Codex sessions and hosted agents.
- The shared seed includes a directive to make a Telora planning call the first tool action on build or new-capability requests.
- Daemon startup refreshes the shared seed when the relevant configuration and existing file are present.
- The reviewed runtime locations concern worktree dependency installation and script analysis, Lacuna configuration reload, and rendering install-script text; they do not establish an attack.
- The shared instruction write is part of explicit harness setup; the reviewed source does not show credential transfer or a confirmed malicious payload.
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@0.23.48.
See all versions of @telora/daemon for other recorded verdicts.
- Review the evidence and your use of @telora/daemon@0.23.48 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.