@vatio-ai/cli@0.79.0
Vatio CLI — deploy and manage Vatio agent workspaces
AI Security Review
scanned 24d ago · by lpm-firewall-aiThe reviewed source shows a bounded, user-invoked AGENTS.md setup capability, which warrants a warning under the agent integration policy. No concrete malicious behavior or npm lifecycle trigger was found.
Static reason
No blocking static signals were detected.
Trigger
A user runs `vatio init` in a project directory.
Impact
The project’s coding agent may follow the added Vatio workflow guidance; the inspected code does not show an automatic install-triggered write.
Mechanism
The command creates AGENTS.md or appends the Vatio guidance section if the existing file does not mention Vatio.
AI rationale
The reviewed source shows a bounded, user-invoked AGENTS.md setup capability, which warrants a warning under the agent integration policy. No concrete malicious behavior or npm lifecycle trigger was found.
Evidence
AGENTS.md
Decision evidence
public snapshotAI called this Suspicious at 79.0% confidence as Dangerous Capability with medium false-positive risk.
Evidence for warning
- The package exposes a command-line entry point and declares no npm lifecycle scripts.
- The explicit `vatio init` command writes a Vatio guidance section into the project’s AGENTS.md file when it is absent or does not already mention Vatio.
- The skills hint inspects Claude plugin and project skill locations; its network check fetches the Vatio skills package version and stores local check state.
- Sharing a session requires confirmation in an interactive terminal, or an explicit yes flag.
Evidence against
- The AGENTS.md write is reached through the explicit init command, not an npm install hook.
- The inspected skills-hint code reads agent installation metadata and caches a reminder timestamp; it does not install or update an agent plugin.
- Session sharing has a confirmation gate before sending the transcript.
Behavioral surface
ChildProcessCryptoEnvironmentVarsFilesystemNetwork
Source & flagged code
6 flaggedlib/skills-hint.mjsView file
•Manifest-trigger-reachable source links an external AI-agent control path to a behavior-bearing write operation.
import { existssync, mkdirsync, readfilesync, writefilesync } from "node:fs";
import { homedir } from "node:os";
import { dirname, join, resolve } from "node:path";
import { confighome } from "./config.mjs";
import { paint } from "./support.mjs";
const skill = "vatio-improve";
const version_file = ".vatio-sk[redacted]";
const latest_url = "https://registry.npmjs.org/@vatio-ai/skills/latest";
const show_every_ms = 24 * 60 * 60 * 1000;
const check_every_ms = 24 * 60 * 60 * 1000;
const fetch_timeout_ms = 1_500;
export async function printskillshint(startdir = process.cwd()) {
if (process.env.ci || process.env.vatio_no_skills_hint) return;
const path = join(confighome(), "sk
High
Trigger Reachable External Ai Agent Control Surface Mutation
Manifest-trigger-reachable source writes behavior-bearing configuration into a user or project AI-agent control surface.
lib/skills-hint.mjsView on unpkg77".claude");
const found = [];
const plugin = pluginVersion(join(claudeHome, "plugins", "installed_plugins.json"));
if (plugin !== undefined) found.push({ kind: "plugin", vers
Medium
Ai Review Evidence
The skills hint inspects Claude plugin and project skill locations; its network check fetches the Vatio skills package version and stores local check state.
lib/skills-hint.mjsView on unpkg · L77Findings
2 High6 Medium4 Low
HighTrigger Reachable External Ai Agent Control Surface Mutationlib/skills-hint.mjs
HighSemantic Analysis Limitedlib/commands/support-commands.mjs#virtual:normalized:round1
MediumNetwork
MediumEnvironment Vars
MediumSuspicious Lifecycle Evidencepackage.json
MediumAi Review Evidencelib/commands/misc.mjs
MediumAi Review Evidencelib/commands/misc.mjs
MediumAi Review Evidencelib/skills-hint.mjs
LowFilesystem
LowHigh Entropy Strings
LowUrl Strings
LowNo License
Affected versions and remediation
This report applies to @vatio-ai/cli@0.79.0.
See all versions of @vatio-ai/cli for other recorded verdicts.
- Review the evidence and your use of @vatio-ai/cli@0.79.0 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.