@telora/daemon@0.22.293
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 user-command mutation of agent configuration, including hook and MCP setup. I found no concrete malicious chain or install-time agent-control mutation.
Decision evidence
public snapshot- The connect flow writes agent instructions and harness configuration, including Claude settings hooks and MCP registrations, as part of an explicit CLI setup command.
- The repository root and daemon configuration are package-aligned setup destinations; no unconsented npm install hook is declared.
- The reviewed snippets show no confirmed credential exfiltration or attack.
- package.json declares only prepublishOnly, which builds and stamps package metadata; it has no preinstall, install, or postinstall hook.
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@0.22.293.
See all versions of @telora/daemon for other recorded verdicts.
- Review the evidence and your use of @telora/daemon@0.22.293 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.