alvin-bot@5.97.0
Open-source, self-hosted autonomous AI agent on Telegram, Slack, Discord, WhatsApp, Signal, terminal & web. Claude Agent SDK + multi-provider engine with auto-failover, detached sub-agents, zero-config memory. Local-first, telemetry-free.
AI Security Review
scanned 1mo ago · by lpm-firewall-aiThe inspected package has no install lifecycle hook and its powerful behaviors are exposed as runtime CLI or agent functionality. Obfuscation warrants caution but does not by itself establish malicious behavior.
Decision evidence
public snapshot- Package metadata exposes a CLI and start/setup scripts; no registry install lifecycle hook was present in the inspected scripts.
- The Claude bridge starts a local Claude executable with piped standard streams.
- The command executor contains agent command execution, while the CLI routes setup only when the user supplies the setup command.
- The web server contains password-based authentication checks, and the email plugin sends only caller-provided recipient, subject, and body values through its configured mail CLI.
- Several distributed files are obfuscated, limiting readability.
- The package intentionally provides powerful agent capabilities, including shell commands and email sending.
Source & flagged code
19 flagged · loading sourcePackage source references child process execution.
claude-bridge/src/claude.jsView on unpkg · L2Package source references dynamic require/import behavior.
claude-bridge/src/claude.jsView on unpkg · L2Package source references weak cryptographic algorithms.
claude-bridge/src/claude.jsView on unpkg · L2Findings
Affected versions and remediation
This report applies to alvin-bot@5.97.0.
See all versions of alvin-bot for other recorded verdicts.
- Review the evidence and your use of alvin-bot@5.97.0 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.