triflux@10.70.0
CLI-first multi-model orchestrator for Claude Code — route tasks to Codex, Antigravity, and Claude
AI Security Review
scanned 9d ago · by lpm-firewall-aiThe install hook automatically installs package-owned agent skills, so this merits a warning under the agent extension lifecycle policy. The inspected source does not support a malicious verdict or publish block.
Decision evidence
public snapshot- The manifest runs the setup script during npm postinstall, and installed copies invoke its deferred setup path.
- Deferred setup calls skill synchronization automatically; that code copies package-provided Markdown skills into Claude and Codex skill directories.
- Other indicated source locations refer to user-level Claude and Codex configuration, legacy configuration cleanup, model settings, and local report storage; they did not establish a separate attack chain.
- The reviewed install path did not establish credential harvesting, external data transfer, or remote payload execution.
- The integration installs this package's own skills, which matches its multi-model orchestration purpose.
- The inspected postinstall path did not establish credential theft or another concrete malicious attack.
Source & flagged code
25 flagged · loading sourcePackage defines install-time lifecycle scripts.
package.jsonView on unpkgPackage source references shell execution.
Findings
Affected versions and remediation
This report applies to triflux@10.70.0.
See all versions of triflux for other recorded verdicts.
- Review the evidence and your use of triflux@10.70.0 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.