oh-my-claude-sisyphus
Multi-agent orchestration system for Claude Code - Inspired by oh-my-opencode
This report shows the evidence for oh-my-claude-sisyphus@5.7.30. 0 of 44 known versions are blocked or flagged. See all versions.
AI Security Review
scanned 3d ago · by lpm-firewall-aiThe install hook only invokes the package's optional local native build. The inspected outbound feature requires both a Typesafe key and explicit per-point opt-in, so no malicious default behavior was identified.
Decision evidence
public snapshot- The postinstall hook skips development installs, non-macOS platforms, and installs where the native addon already exists; otherwise it runs the package's optional local build script.
- The Jev feature requires a Typesafe API key and explicit OMC_JEV point opt-in; a key alone enables no requests.
- When enabled, Jev posts judgment state and questions to api.typesafe.ai using the supplied Typesafe key.
Source & flagged code
24 flaggedPackage defines install-time lifecycle scripts.
package.jsonView on unpkgPackage source references child process execution.
dist/autoresearch/runtime.jsView on unpkg · L1Findings
Affected versions and remediation
This report applies to oh-my-claude-sisyphus@5.7.30.
The versions list below shows the verdict for each recorded version.
- Review the evidence and your use of oh-my-claude-sisyphus@5.7.30 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.