registry / @vatio-ai/skills / 1.28.1
@vatio-ai/skills@1.28.1
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 6d ago · by lpm-firewall-aiThe package has no lifecycle hook or automatic runtime behavior. Its installer copies its own skills only when explicitly invoked, and the instructions for sharing a coding session require user agreement before sending.
Static reason
No blocking static signals were detected.
Trigger
A user runs `vatio-skills` or `npx @vatio-ai/skills`.
Impact
The project’s coding agents can use Vatio skills; no unauthorized data transfer or broader agent-setting change was identified.
Mechanism
The CLI copies skill directories into the project’s `.agents/skills` and `.claude/skills` paths. Session sharing instructions require the user’s agreement before sending.
AI rationale
The package has no lifecycle hook or automatic runtime behavior. Its installer copies its own skills only when explicitly invoked, and the instructions for sharing a coding session require user agreement before sending.
Evidence
.agents/skills/<skill>/.claude/skills/<skill>/.vatio-skills-version
Decision evidence
public snapshotAI called this Clean at 96.0% confidence as Benign with low false-positive risk.
Evidence for AI clean decision
- The manifest exposes the installer as a CLI binary and contains no lifecycle hook; the README says the skills have no hooks or anything that runs by itself.
- The installer uses the current directory by default and copies this package’s skills into `.agents/skills` and `.claude/skills` when run.
- The session-sharing instructions require showing the user what would be sent and prohibit sending without their agreement.
- The README describes session sharing as optional and says it occurs only after the user agrees.
Evidence against
- The installer can overwrite installed skill copies and remove certain retired copies, but only when the user invokes the CLI.
- The package’s skills can direct an agent to use the Vatio CLI and service as part of the package’s stated purpose.
Behavioral surface
Filesystem
UrlStrings
Source & flagged code
8 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-analyze,
vatio-share-session) into path/.ag
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-analyze,
vatio-share-
Findings
2 High8 Low
HighExternal Ai Agent Control Surface Mutationbin/install.mjs
HighTrigger Reachable External Ai Agent Control Surface Mutationbin/install.mjs
LowFilesystem
LowUrl Strings
LowSuspicious Lifecycle Evidencepackage.json
LowSuspicious Lifecycle EvidenceREADME.md
LowAi Review Evidencebin/install.mjs
LowAi Review Evidencebin/install.mjs
LowAi Review Evidenceskills/vatio-share-session/SKILL.md
LowAi Review Evidenceskills/vatio-share-session/SKILL.md
Affected versions and remediation
This report applies to @vatio-ai/skills@1.28.1.
See all versions of @vatio-ai/skills for other recorded verdicts.
- Review the evidence and your use of @vatio-ai/skills@1.28.1 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.