oh-my-claude-sisyphus@5.2.0
Multi-agent orchestration system for Claude Code - Inspired by oh-my-opencode
AI Security Review
scanned 2mo ago · by lpm-firewall-aiNo malicious install hook, credential theft, or remote-code execution chain was confirmed. The automatic global self-update and Claude extension reconciliation justify a warning for lifecycle risk.
Decision evidence
public snapshot- The shipped CLI contains a silent-update path that defaults to applying updates and installs the latest package globally.
- The package has broad user-invoked command, worktree, language-server, and worker-launch capabilities.
- This is a first-party Claude Code extension update mechanism, but automatic runtime replacement remains a supply-chain risk.
- package.json has only a prepublishOnly hook, not an install-time lifecycle hook.
- No source evidence showed credential collection or transmission to an unrelated endpoint.
- The update path is gated by a configuration setting and the explicit update command is user-invoked.
Source & flagged code
25 flaggedPackage source references child process execution.
dist/autoresearch/runtime.jsView on unpkg · L1Findings
Affected versions and remediation
This report applies to oh-my-claude-sisyphus@5.2.0.
See all versions of oh-my-claude-sisyphus for other recorded verdicts.
- Review the evidence and your use of oh-my-claude-sisyphus@5.2.0 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.