oh-my-claude-sisyphus@5.7.7
⚠ Under reviewMulti-agent orchestration system for Claude Code - Inspired by oh-my-opencode
AI Security Review
scanned 14d ago · by lpm-firewall-aiThe inspected install hook performs an optional platform-specific native build, and the CLI dynamic-code hint is consistent with schema validation. The unresolved source for a selected runtime dependency prevents a clean verdict, but provides no independent evidence of malicious behavior.
Decision evidence
public snapshot- package.json declares @anthropic-ai/claude-agent-sdk as a runtime dependency, but its source could not be resolved in the supplied inspection evidence.
- The package imports that SDK for its MCP server and dynamically loads it for agent queries, so the unresolved dependency is relevant to runtime behavior.
- The postinstall hook skips non-macOS platforms and only attempts an optional native build on macOS.
- The CLI bundle’s dynamic function construction is part of schema validation, with the schema supplied to the validator.
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@5.7.7.
See all versions of oh-my-claude-sisyphus for other recorded verdicts.
- Review the evidence and your use of oh-my-claude-sisyphus@5.7.7 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.