@vatio-ai/skills@1.28.0
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 hooks, and the flagged writes occur only when a user runs the installer; they are limited to the intended project-local skill directories. The inspected skill instructions describe Vatio workflows and require user consent for session sharing.
Decision evidence
public snapshot- The manifest exposes bin/install.mjs as a CLI and declares no lifecycle scripts.
- When invoked, the installer copies package skills into .agents/skills and .claude/skills and writes a version marker there.
- The README describes the skills as instructions with no hooks, MCP servers, or automatic execution.
- The session-sharing skill requires asking the user before sending a session.
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@1.28.0.
See all versions of @vatio-ai/skills for other recorded verdicts.
- Review the evidence and your use of @vatio-ai/skills@1.28.0 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.