registry / @vatio-ai/skills / 1.13.0
@vatio-ai/skills@1.13.0
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 23d ago · by lpm-firewall-aiThe package’s command installs bundled instructions into coding-agent skill folders, which is a concrete agent extension capability. Because this requires explicit command execution and no malicious behavior was established, classify it as suspicious and warn.
Static reason
No blocking static signals were detected.
Trigger
A user runs the vatio-skills command.
Impact
The installed instructions can affect how coding agents behave in that project.
Mechanism
The installer recursively copies the bundled skills into .agents/skills and .claude/skills, replacing existing copies.
AI rationale
The package’s command installs bundled instructions into coding-agent skill folders, which is a concrete agent extension capability. Because this requires explicit command execution and no malicious behavior was established, classify it as suspicious and warn.
Evidence
bin/install.mjs.agents/skills.claude/skills
Decision evidence
public snapshotAI called this Suspicious at 90.0% confidence as Dangerous Capability with high false-positive risk.
Evidence for warning
- The manifest exposes bin/install.mjs as a command and declares no npm lifecycle hooks.
- When run, the installer copies bundled skills into project-level .agents/skills and .claude/skills folders, overwriting existing copies.
- The session-sharing skill instructs the agent to ask the user before sending a session.
Evidence against
- The agent-skill folder changes require an explicit command invocation; the inspected source does not show automatic install-time mutation.
- No malicious payload or hidden data transfer was identified in the reviewed installer.
Behavioral surface
Filesystem
UrlStrings
Source & flagged code
5 flaggedbin/install.mjsView file
•Runtime or CLI code links a write operation to an explicit external AI-agent control path:
#!/usr/bin/env node
import { cpsync, existssync, readfilesync, readdirsync, rmsync, writefilesync } from "node:fs";
import { dirname, join, relative } from "node:path";
import { fileurltopath } from "node:url";
const usage = `usage: npx @vatio-ai/skills [--dir path]
copies the vatio skills (vatio-init, vatio-improve, vatio-share-session) into
path/.agents/skills and
High
External Ai Agent Control Surface Mutation
Runtime or CLI source writes behavior-bearing configuration into a user or project AI-agent control surface.
bin/install.mjsView on unpkg•Manifest-trigger-reachable source links an external AI-agent control path to a behavior-bearing write operation.
#!/usr/bin/env node
import { cpsync, existssync, readfilesync, readdirsync, rmsync, writefilesync } from "node:fs";
import { dirname, join, relative } from "node:path";
import { fileurltopath } from "node:url";
const usage = `usage: npx @vatio-ai/skills [--dir path]
copies the vatio skills (vatio-init, vatio-improve, vatio-share-session) into
p
Findings
2 High3 Medium2 Low
HighExternal Ai Agent Control Surface Mutationbin/install.mjs
HighTrigger Reachable External Ai Agent Control Surface Mutationbin/install.mjs
MediumSuspicious Lifecycle Evidencepackage.json
MediumAi Review Evidencebin/install.mjs
MediumAi Review Evidenceskills/vatio-share-session/SKILL.md
LowFilesystem
LowUrl Strings
Affected versions and remediation
This report applies to @vatio-ai/skills@1.13.0.
See all versions of @vatio-ai/skills for other recorded verdicts.
- Review the evidence and your use of @vatio-ai/skills@1.13.0 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.