oh-my-claude-sisyphus@5.0.0
Multi-agent orchestration system for Claude Code - Inspired by oh-my-opencode
AI Security Review
scanned 2mo ago · by lpm-firewall-aiSource confirms an opt-in automatic self-update path and first-party plugin registry mutation. The manifest lacks install-time lifecycle hooks and inspection found no concrete exfiltration or malicious payload chain.
Decision evidence
public snapshot- Session-start hook invokes silent-update initialization.
- Opt-in silent update fetches GitHub release data and runs a global npm install.
- Update code rewrites only its own OMC plugin registry entries and cache.
- package.json has no preinstall/install/postinstall hook.
- Silent updates default disabled when config is absent or invalid.
- No credential harvesting or exfiltration beyond GitHub update requests was found.
Source & flagged code
15 flaggedPackage source references child process execution.
dist/autoresearch/runtime.jsView on unpkg · L1Package source references a known benign dynamic code generation pattern.
Findings
Affected versions and remediation
This report applies to oh-my-claude-sisyphus@5.0.0.
See all versions of oh-my-claude-sisyphus for other recorded verdicts.
- Review the evidence and your use of oh-my-claude-sisyphus@5.0.0 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.