@vatio-ai/skills@1.11.0
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 24d ago · by lpm-firewall-aiThe package provides an explicit CLI that installs its own agent skills into project configuration locations, so this is a guarded agent capability warranting a warning. The inspected manifest has no lifecycle scripts, and the session-sharing instructions describe a user request or offer/check gate; no concrete attack was established.
Decision evidence
public snapshot- package.json exposes bin/install.mjs as a CLI entry point.
- When run, the installer copies bundled skills into .agents/skills and .claude/skills, overwriting existing copies.
- The session-sharing skill describes sending a session only when the user asks or after an offer and a CLI check.
- The installer is a CLI entry point; the inspected package manifest defines no lifecycle scripts.
- The inspected sharing instructions include an ask/check step before the session is prepared for sending.
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@1.11.0.
See all versions of @vatio-ai/skills for other recorded verdicts.
- Review the evidence and your use of @vatio-ai/skills@1.11.0 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.