oh-my-claude-sisyphus@5.7.29
Multi-agent orchestration system for Claude Code - Inspired by oh-my-opencode
AI Security Review
scanned 3d ago · by lpm-firewall-aiThe postinstall hook only attempts a local optional native build on macOS. The reviewed network feature requires a separate service key and explicit point configuration, and I found no concrete attack behavior.
Decision evidence
public snapshot- The postinstall hook skips non-macOS platforms and only attempts to build the package’s optional native addon locally.
- The Jev request feature requires a TYPESAFE_API_KEY and explicit OMC_JEV point selection; it is off when those are absent.
- Jev sends its configured request to api.typesafe.ai using the separately named TYPESAFE_API_KEY.
- The CLI includes network and shell execution capabilities, but the inspected paths serve configurable product features and do not show automatic unrelated collection.
- No install-time network request or unrelated credential forwarding was identified in the inspected lifecycle and CLI paths.
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@5.7.29.
See all versions of oh-my-claude-sisyphus for other recorded verdicts.
- Review the evidence and your use of oh-my-claude-sisyphus@5.7.29 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.