@vatio-ai/skills@1.27.1
Vatio skills for Claude Code, Cursor and Codex: add an AI agent to the app you're building with /vatio-init, then improve it daily with /vatio-improve and learn what people ask it with /vatio-analyze.
AI Security Review
scanned 6d ago · by lpm-firewall-aiThe manifest has no lifecycle scripts or import entry point, and its CLI performs project-local skill installation only when explicitly invoked. The reviewed skill instructions describe user-triggered workflows and require agreement before sharing a coding session.
Decision evidence
public snapshot- The manifest exposes a CLI binary and no import entry point; it has no lifecycle scripts.
- The installer runs when invoked and copies the package’s skills into project-local .agents/skills and .claude/skills directories.
- Session sharing instructions require showing the user what would be sent and getting their agreement before sending.
- The README describes the skills as instructions with no hooks, MCP servers, or automatic execution.
Source & flagged code
7 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@1.27.1.
See all versions of @vatio-ai/skills for other recorded verdicts.
- Review the evidence and your use of @vatio-ai/skills@1.27.1 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.