triflux@10.63.0
CLI-first multi-model orchestrator for Claude Code — route tasks to Codex, Antigravity, and Claude
AI Security Review
scanned 11d ago · by lpm-firewall-aiThe postinstall hook performs first-party agent setup by synchronizing package skills into Claude's configuration. This warrants a warning under the agent integration policy, while the inspected behavior does not support a malicious verdict.
Decision evidence
public snapshot- The package runs scripts/setup.mjs from its postinstall hook.
- During setup, syncSkills copies package skill files into the user's Claude skills directory.
- Setup gates Codex hook approval and several optional installs on user consent.
- The inspected source shows package-owned skill setup, not an unconsented foreign control-surface change or credential exfiltration.
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@10.63.0.
See all versions of triflux for other recorded verdicts.
- Review the evidence and your use of triflux@10.63.0 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.