triflux@10.78.0
CLI-first multi-model orchestrator for Claude Code — route tasks to Codex, Antigravity, and Claude
AI Security Review
scanned 7d ago · by lpm-firewall-aiThe manifest activates setup during postinstall, and setup modifies Claude agent settings without a separate user command. This supports a warning for first-party agent configuration lifecycle risk, but the inspected source does not establish malicious data transfer or another concrete attack.
Decision evidence
public snapshot- package.json runs scripts/setup.mjs during postinstall.
- For an installed package, the postinstall branch falls through to runDeferred.
- Setup applies its Claude settings changes during that run and persists them.
- It enables experimental agent teams and sets teammateMode to auto when unset.
- The background MCP inventory check builds and writes a local cache.
- The inspected install path does not establish an unrelated installation identifier transfer.
- The setup’s consent steps separately handle optional installs and Codex hook approval.
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@10.78.0.
See all versions of triflux for other recorded verdicts.
- Review the evidence and your use of triflux@10.78.0 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.