@vatio-ai/skills@1.6.0
Agent skills for building and improving a Vatio agent from your coding agent: Claude Code, Codex, Cursor, Gemini CLI, Copilot and any agent that reads SKILL.md
AI Security Review
scanned 25d ago · by lpm-firewall-aiThe package’s explicit CLI performs first-party skill setup in the project’s agent directories, which warrants a warning for agent capability mutation. No automatic lifecycle trigger or concrete malicious behavior was established.
Decision evidence
public snapshot- The package exposes bin/install.mjs as the vatio-skills command.
- When invoked, the installer copies its bundled skills into the project’s .agents/skills and .claude/skills directories, replacing existing copies.
- The installer removes a renamed skill only when its SKILL.md identifies it as the old vatio-new skill.
- package.json declares no lifecycle scripts, so the installer is not configured to run automatically during installation.
- The inspected installer has no network or credential-handling behavior.
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@1.6.0.
See all versions of @vatio-ai/skills for other recorded verdicts.
- Review the evidence and your use of @vatio-ai/skills@1.6.0 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.