oh-my-claude-sisyphus@5.7.4
⚠ Under reviewMulti-agent orchestration system for Claude Code - Inspired by oh-my-opencode
AI Security Review
scanned 19d ago · by lpm-firewall-aiThe inspected postinstall behavior is a platform-gated optional native build, and the credential-related excerpts show a Typesafe-keyed configurable request plus Anthropic usage requests to api.anthropic.com. A clean decision requires citations for 139 distinct paths, exceeding the 128-citation limit, so this review remains unresolved without a confirmed attack finding.
Decision evidence
public snapshot- package.json runs a postinstall hook that invokes a native build script.
- The postinstall script skips non-macOS platforms and attempts an optional native build on macOS.
- The Typesafe-backed feature reads TYPESAFE_API_KEY and permits an OMC_JEV_ENDPOINT override.
- That feature passes its configured endpoint and key to its request helper.
- Usage checks send Anthropic credentials to api.anthropic.com.
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@5.7.4.
See all versions of oh-my-claude-sisyphus for other recorded verdicts.
- Review the evidence and your use of oh-my-claude-sisyphus@5.7.4 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.