oh-my-claude-sisyphus@5.7.21
Multi-agent orchestration system for Claude Code - Inspired by oh-my-opencode
AI Security Review
scanned 6d ago · by lpm-firewall-aiThe install hook only attempts a local native build, and the flagged outbound path belongs to a documented Jev feature that requires explicit configuration. Its API key is a Jev credential, and the reviewed code does not redirect Anthropic credentials to that service.
Decision evidence
public snapshot- The postinstall hook is limited to an optional local native build; the build script uses local Node headers and does not download binaries.
- Jev requires a configured API key and judgment points, and the README documents its modes and states that it sends nothing without configuration.
- When enabled, Jev sends bounded state and questions to its documented API endpoint using the Jev API key; this is an explicit integration, not an Anthropic credential redirect.
- When configured, Jev sends orchestration state and questions to api.typesafe.ai/v1/systemone, which may include excerpts of user task context.
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@5.7.21.
See all versions of oh-my-claude-sisyphus for other recorded verdicts.
- Review the evidence and your use of oh-my-claude-sisyphus@5.7.21 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.