triflux@10.62.0
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 lifecycle hook automatically performs first-party agent setup, which meets the warning threshold for package-owned agent extension setup. The inspected code does not establish an unconsented broad control-surface attack or another concrete malicious chain.
Decision evidence
public snapshot- The npm postinstall hook runs scripts/setup.mjs.
- Setup synchronizes package skills into the user's Claude skills directory during setup.
- The setup entrypoint runs deferred setup for an installed package; checkout postinstall is limited to printing a message.
- Codex hooks are registered without trust by default, and approval requires an interactive consent prompt.
- The inspected behavior supports first-party setup for the package's agent tooling; no concrete attack behavior was established.
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@10.62.0.
See all versions of triflux for other recorded verdicts.
- Review the evidence and your use of triflux@10.62.0 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.