oh-my-claude-sisyphus@5.7.11
⚠ Under reviewMulti-agent orchestration system for Claude Code - Inspired by oh-my-opencode
AI Security Review
scanned 12d ago · by lpm-firewall-aiThe package’s install hook is a guarded optional native build, and the inspected source did not establish attack behavior. The directly used Agent SDK remains unresolved, so this snapshot does not support a clean verdict.
Decision evidence
public snapshot- The manifest declares the Anthropic Agent SDK as a runtime dependency, and shipped runtime modules import it directly.
- The package snapshot does not resolve the SDK implementation, so its behavior cannot be assessed from the available source.
- The npm postinstall hook skips development and non-macOS installs, and only attempts to build the optional native module.
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@5.7.11.
See all versions of oh-my-claude-sisyphus for other recorded verdicts.
- Review the evidence and your use of oh-my-claude-sisyphus@5.7.11 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.