@telora/daemon@0.22.42
Agent orchestration daemon for Telora - spawns and manages Claude Code instances
AI Security Review
scanned 1mo ago · by lpm-firewall-aiThis package exposes risky remote-agent and AI configuration capabilities, including disabled Claude permission checks. The actions are user-command initiated and there is no install-time execution or demonstrated theft, so the evidence supports a warning rather than a block.
Decision evidence
public snapshot- The daemon launches Claude with permission checks disabled for accepted remote requests.
- The explicit connect command can install and start a global copy of this package.
- The connect flow merges tracking hooks into a user's Claude settings when a companion binary is present.
- Runtime auto-update installs the latest package globally.
- package.json has no preinstall, install, or postinstall hook and no dependency on itself.
- The configuration writes and daemon start are reached through explicit CLI connect/setup behavior, not package installation.
- No direct credential harvesting or unrelated data exfiltration was found in the inspected paths.
Source & flagged code
7 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@0.22.42.
See all versions of @telora/daemon for other recorded verdicts.
- Review the evidence and your use of @telora/daemon@0.22.42 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.