oh-my-claude-sisyphus@5.7.25
Multi-agent orchestration system for Claude Code - Inspired by oh-my-opencode
AI Security Review
scanned 4d ago · by lpm-firewall-aiThe install hook performs only a platform-gated optional native build and does not contact a host. The fixed Jev endpoint is used only when configured with an API key and selected points, and the endpoint can be overridden.
Decision evidence
public snapshot- The postinstall hook only attempts to build the optional native module on macOS; it exits on other platforms.
- Jev is disabled unless TYPESAFE_API_KEY is set and it is not explicitly switched off; configured points determine whether it runs.
- Jev sends its state and questions to a configurable endpoint, with api.typesafe.ai as the default.
- The CLI exposes configuration installation as an explicit `omc install` command.
Source & flagged code
23 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@5.7.25.
See all versions of oh-my-claude-sisyphus for other recorded verdicts.
- Review the evidence and your use of oh-my-claude-sisyphus@5.7.25 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.