@vatio-ai/skills@1.14.0
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 manifest defines a CLI binary but no npm lifecycle hooks, and the installer writes first-party skills only when explicitly run. The packaged session-sharing instructions require user consent before sending a session.
Decision evidence
public snapshot- package.json exposes bin/install.mjs as a CLI and defines no lifecycle hooks.
- The installer documents an explicit npx command and copies packaged skills into project-level .agents/skills and .claude/skills directories.
- The installer removes a renamed skill directory only when its SKILL.md identifies it as package-installed.
- The session-sharing skill says not to send a session independently; sending requires the user's request or affirmative choice.
Source & flagged code
8 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@1.14.0.
See all versions of @vatio-ai/skills for other recorded verdicts.
- Review the evidence and your use of @vatio-ai/skills@1.14.0 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.