oh-my-claude-sisyphus@5.7.22
Multi-agent orchestration system for Claude Code - Inspired by oh-my-opencode
AI Security Review
scanned 5d ago · by lpm-firewall-aiThe install hook is limited to an optional macOS native build. The suspicious gateway flow is an opt-in Jev integration using a dedicated Typesafe key and configurable endpoint; the reviewed source does not show automatic redirection of an Anthropic credential.
Decision evidence
public snapshot- The postinstall hook skips non-macOS platforms and only attempts to build the package’s optional native addon.
- The Jev client reads a dedicated TYPESAFE_API_KEY and sends requests only for configured judgment points; its endpoint can be overridden.
- The CLI bin delegates to bridge/cli.cjs, where the reviewed Jev flow is configuration-gated.
- When enabled, Jev sends bounded state and questions with a bearer key to its configured endpoint; the default is https://api.typesafe.ai/v1/systemone. This is an explicit external-service integration, not an Anthropic-key redirect.
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@5.7.22.
See all versions of oh-my-claude-sisyphus for other recorded verdicts.
- Review the evidence and your use of oh-my-claude-sisyphus@5.7.22 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.