registry / @vatio-ai/skills / 1.30.1
@vatio-ai/skills@1.30.1
Vatio skills for Claude Code, Cursor and Codex: add an AI agent to the app you're building with /vatio-init, then improve it daily with /vatio-improve and learn what people ask it with /vatio-analyze.
AI Security Review
scanned 5d ago · by lpm-firewall-aiThe package's installer performs the advertised project-level skill setup when explicitly invoked. Its disclosed install telemetry sends limited metadata to Vatio and has an opt-out; the skill's suggested project permission change requires user approval.
Static reason
No blocking static signals were detected.
Trigger
The user runs the vatio-skills CLI; no package lifecycle scripts are declared.
Impact
The observed behavior is consistent with the package's stated purpose; no unauthorized credential access, project-data collection, or agent-setting change was identified.
Mechanism
The CLI copies skill files into project-level agent directories and reports installation metadata to Vatio.
AI rationale
The package's installer performs the advertised project-level skill setup when explicitly invoked. Its disclosed install telemetry sends limited metadata to Vatio and has an opt-out; the skill's suggested project permission change requires user approval.
Evidence
.agents/skills/<skill>/.vatio-skills-version.claude/skills/<skill>/.vatio-skills-version~/.vatio/sessions.json
Network endpoints1
vatio.ai/api/developer/v1/cli/events
Decision evidence
public snapshotAI called this Clean at 95.0% confidence as Benign with low false-positive risk.
Evidence for AI clean decision
- The package exposes bin/install.mjs as an explicitly invoked CLI; package.json declares no lifecycle scripts.
- The installer copies skills into the project's .agents/skills and .claude/skills directories when run.
- Install telemetry is disclosed, can be disabled with VATIO_TELEMETRY=0 or DO_NOT_TRACK=1, and is described as sending only the version, coding agent and session identifier.
- The vatio-init skill says to offer the project permission rule only with the user's approval and not to edit the global Claude settings file.
- The README describes the skills as instructions with no hooks or code that runs by itself.
Evidence against
Behavioral surface
ChildProcessCryptoEnvironmentVarsFilesystemNetwork
UrlStrings
Source & flagged code
7 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 { spawnsync } from "node:child_process";
import { randomuuid } from "node:crypto";
import { cpsync, existssync, mkdirsync, readfilesync, readdirsync, rmsync, writefilesync } from "node:fs";
import { homedir, platform } from "node:os";
import { basename, dirname, join, relative, resolve } from "node:path";
import { fileurltopath } from "node:
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 { spawnsync } from "node:child_process";
import { randomuuid } from "node:crypto";
import { cpsync, existssync, mkdirsync, readfilesync, readdirsync, rmsync, writefilesync } from "node:fs";
import { homedir, platform } from "node:os";
import { basename, dirname, join, relative, resolve } from "node:path";
import { fileu
Findings
2 High2 Medium7 Low
HighExternal Ai Agent Control Surface Mutationbin/install.mjs
HighTrigger Reachable External Ai Agent Control Surface Mutationbin/install.mjs
MediumNetwork
MediumEnvironment Vars
LowFilesystem
LowUrl Strings
LowSuspicious Lifecycle Evidencepackage.json
LowAi Review Evidencebin/install.mjs
LowAi Review Evidencebin/install.mjs
LowAi Review Evidenceskills/vatio-init/SKILL.md
LowAi Review EvidenceREADME.md
Affected versions and remediation
This report applies to @vatio-ai/skills@1.30.1.
See all versions of @vatio-ai/skills for other recorded verdicts.
- Review the evidence and your use of @vatio-ai/skills@1.30.1 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.