oh-my-claude-sisyphus@5.7.19
⚠ Under reviewMulti-agent orchestration system for Claude Code - Inspired by oh-my-opencode
AI Security Review
scanned 9d ago · by lpm-firewall-aiThe inspected postinstall path is a guarded optional native build, and the bridge's dynamic function generates a schema validator. The runtime dependency @anthropic-ai/claude-agent-sdk is selected by the package and imported during agent execution, but its source was unresolved, so a clean verdict is not supported.
Decision evidence
public snapshot- The postinstall hook skips non-macOS systems and attempts only an optional native build on macOS.
- The package declares the Claude Agent SDK as a runtime dependency and imports it in agent execution paths.
- The bridge's dynamic function constructs a schema validator from generated validation code.
- The inspected test location creates a security regression fixture; this does not establish an attack.
- No concrete malicious behavior was established in the inspected source excerpts.
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@5.7.19.
See all versions of oh-my-claude-sisyphus for other recorded verdicts.
- Review the evidence and your use of oh-my-claude-sisyphus@5.7.19 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.