@vatio-ai/cli@0.77.0
Vatio CLI — deploy and manage Vatio agent workspaces
AI Security Review
scanned 24d ago · by lpm-firewall-aiSource inspection found an explicit-command write to project agent instructions, which merits a capability warning under the agent configuration policy. The inspected code did not establish install-time execution or a concrete attack.
Static reason
No blocking static signals were detected.
Trigger
A user runs the vatio init command in a project directory.
Impact
This adds package-controlled instructions to the project agent context; no attack was established beyond this guarded setup capability.
Mechanism
The command creates or appends a Vatio-specific section in that directory's AGENTS.md file.
AI rationale
Source inspection found an explicit-command write to project agent instructions, which merits a capability warning under the agent configuration policy. The inspected code did not establish install-time execution or a concrete attack.
Evidence
lib/commands/misc.mjsAGENTS.md
Decision evidence
public snapshotAI called this Suspicious at 91.0% confidence as Dangerous Capability with medium false-positive risk.
Evidence for warning
- The manifest exposes a CLI entry point and declares no install lifecycle hook.
- Running the explicit init command writes a Vatio guidance note to the project AGENTS.md file.
- The skills hint checks installed skill locations and records hint state; it does not install or update agent extensions.
- Session sharing requires --yes or interactive confirmation before sending the transcript.
Evidence against
- The agent configuration write is tied to an explicit workspace setup command and contains package-specific guidance.
- No install-time attack, credential theft, or unrelated agent-control mutation was identified.
Behavioral surface
ChildProcessCryptoEnvironmentVarsFilesystemNetwork
HighEntropyStringsUrlStrings
NoLicense
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 checks installed skill locations and records hint state; it does not install or update agent extensions.
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@0.77.0.
See all versions of @vatio-ai/cli for other recorded verdicts.
- Review the evidence and your use of @vatio-ai/cli@0.77.0 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.