@vatio-ai/cli@0.87.0
Vatio CLI — deploy and manage Vatio agent workspaces
AI Security Review
scanned 19d ago · by lpm-firewall-aiThe manifest has no install hook, and the flagged AGENTS.md write is limited to the explicit init command. Transcript transfer requires explicit user approval and targets the configured Vatio service, so the inspected source does not establish a malicious attack surface.
Decision evidence
public snapshot- The manifest identifies a CLI entry point and declares yaml as its only dependency; it has no install lifecycle hook.
- The project AGENTS.md note is written during the explicit init command, and existing notes that mention Vatio are left unchanged.
- The skills hint checks agent installation metadata and stores its own display state; it does not write agent instructions or settings.
- Transcript sharing is a separate CLI command. Without --yes it requires an affirmative terminal response, and a noninteractive run without --yes stops without sending.
- When sharing is approved, the CLI posts the transcript to its configured Vatio base URL and uses the configured token for authorization.
- The executable routes the requested command through its dispatcher; its trial retry is limited to a specific trial error. The inspected runtime callers show no automatic agent setup.
Source & flagged code
6 flaggedManifest-trigger-reachable source writes behavior-bearing configuration into a user or project AI-agent control surface.
lib/skills-hint.mjsView on unpkgFindings
Affected versions and remediation
This report applies to @vatio-ai/cli@0.87.0.
See all versions of @vatio-ai/cli for other recorded verdicts.
- Review the evidence and your use of @vatio-ai/cli@0.87.0 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.