oh-my-claude-sisyphus@5.0.1
Multi-agent orchestration system for Claude Code - Inspired by oh-my-opencode
AI Security Review
scanned 2mo ago · by lpm-firewall-aiSource inspection found an opt-in self-update and first-party Claude plugin reconciliation path, but no unconsented install-time mutation, data exfiltration, remote payload execution, or broad foreign-agent control-surface overwrite. The static malicious label is not supported by the inspected source.
Decision evidence
public snapshot- The update command installs the latest package globally and then refreshes its Claude plugin cache.
- The updater changes only registry entries whose plugin ID is this package's own OMC plugin.
- Silent updating can run without interaction, but only after the user has enabled it in the package configuration.
- package.json has no preinstall, install, or postinstall hook.
- Release checks target the package's declared GitHub repository.
- The credential token is used as GitHub API authorization, not sent to an unrelated endpoint.
- The daemon uses an explicit environment allowlist intended to exclude tokens and credentials.
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@5.0.1.
See all versions of oh-my-claude-sisyphus for other recorded verdicts.
- Review the evidence and your use of oh-my-claude-sisyphus@5.0.1 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.