triflux@10.65.1
CLI-first multi-model orchestrator for Claude Code — route tasks to Codex, Antigravity, and Claude
AI Security Review
scanned 11d ago · by lpm-firewall-aiInspected source supports a first-party agent setup capability activated by postinstall, so a warning is appropriate. The scanner's similarity labels do not establish malicious behavior, and the inspected code does not support blocking.
Decision evidence
public snapshot- package.json runs scripts/setup.mjs during postinstall.
- The installed package's postinstall path invokes deferred setup.
- Setup applies status-line, agent-team, and remote-control settings to Claude settings.json.
- Bin entrypoints and inspected agent-related modules show CLI orchestration, session state, and team-file handling consistent with the package's stated purpose.
- Postinstall skips execution from a checkout outside node_modules.
- Inspected setup code does not establish credential exfiltration, unconsented broad agent-control mutation, or malicious behavior.
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@10.65.1.
See all versions of triflux for other recorded verdicts.
- Review the evidence and your use of triflux@10.65.1 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.