savant-code@0.0.29
Multi-Agent AI Coding Assistant with ECHO Protocol
AI Security Review
scanned 3d ago · by lpm-firewall-aiThe package has no install-time hook, and the flagged shell commands are examples embedded in design resources. The launcher downloads and runs the CLI’s release binary, while staged updates are presented for user approval; no concrete attack behavior was found.
Decision evidence
public snapshot- The manifest has no install hook; its scripts run at pack time.
- The CLI entry point runs the launcher only when invoked as the main module.
- The launcher downloads release binaries from the project’s GitHub releases; an environment variable allows a custom release host.
- Update checks stage newer binaries and tell the user they will be installed on a later launch; applying a staged update interactively asks for consent.
- The flagged curl-and-shell commands appear in design analysis resources as UI install-snippet examples, not executed package code.
Source & flagged code
6 flaggedThis package version adds a dangerous source file absent from the previous stored version; route for source-aware review.
launcher.jsView on unpkgFindings
Affected versions and remediation
This report applies to savant-code@0.0.29.
See all versions of savant-code for other recorded verdicts.
- Review the evidence and your use of savant-code@0.0.29 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.