oh-my-claude-sisyphus@5.7.16
⚠ Under reviewMulti-agent orchestration system for Claude Code - Inspired by oh-my-opencode
AI Security Review
scanned 10d ago · by lpm-firewall-aiThe package uses an unresolved runtime dependency in reachable features, so its behavior cannot be fully assessed from this snapshot. The inspected install hook is a platform-gated optional native build, and no concrete attack was established.
Decision evidence
public snapshot- package.json declares @anthropic-ai/claude-agent-sdk as a runtime dependency, and the supplied source snapshot does not include that dependency's source for inspection.
- The package directly imports the SDK to create an MCP server and to run graph agents, so the unresolved dependency is used at runtime.
- The postinstall hook only attempts an optional native build on macOS when the binary is absent; it exits on other platforms.
- No concrete attack was established in the inspected package source.
Source & flagged code
25 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@5.7.16.
See all versions of oh-my-claude-sisyphus for other recorded verdicts.
- Review the evidence and your use of oh-my-claude-sisyphus@5.7.16 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.