@vatio-ai/skills@1.12.0
The Vatio plugin for Claude Code: build a conversational agent for your app with one prompt, then improve it daily with vatio-improve.
AI Security Review
scanned 20d ago · by lpm-firewall-aiThe agent-configuration write occurs only through the exposed command-line installer and copies this package’s own skills into the selected project. The inspected session-sharing instructions require user approval before sending; no malicious behavior was identified.
Decision evidence
public snapshot- The manifest exposes the installer as a command-line tool and declares no lifecycle scripts.
- The installer runs from the current directory by default and accepts a user-provided target directory.
- When run, the installer copies the package’s own skills into project-local agent skill folders.
- The session-sharing instructions require asking before sending a session and say not to send it without the user’s decision.
Source & flagged code
6 flaggedRuntime or CLI source writes behavior-bearing configuration into a user or project AI-agent control surface.
bin/install.mjsView on unpkgFindings
Affected versions and remediation
This report applies to @vatio-ai/skills@1.12.0.
See all versions of @vatio-ai/skills for other recorded verdicts.
- Review the evidence and your use of @vatio-ai/skills@1.12.0 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.