@vatio-ai/skills@1.7.0
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 manifest exposes the installer as a CLI and has no lifecycle hook. Its agent-directory writes are user-invoked and limited to bundled skills, with legacy removal guarded by an ownership check.
Decision evidence
public snapshot- The manifest exposes `bin/install.mjs` as a command-line executable and declares no install lifecycle hook.
- The installer handles command-line arguments and copies the package skills into the project’s `.agents/skills` and `.claude/skills` directories when run.
- Legacy skill removal is limited to copies whose content identifies them as installed by this tool.
Source & flagged code
5 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@1.7.0.
See all versions of @vatio-ai/skills for other recorded verdicts.
- Review the evidence and your use of @vatio-ai/skills@1.7.0 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.