📦

vet

Name: vet
Author: imbue-ai

Content revision r1 High Risk ⚙️ External commands📁 Filesystem access

Review Code Changes with Vet

Code changes can drift from the user request, and tests may miss workflow issues. Vet reviews git diffs and optional session history so agents can catch problems earlier.

Supports: Claude Codex Code(CC)

⚠️ 38 Poor

Stop for confirmation before installing.

Review the plan and obtain explicit user consent before changing files.

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request

Review the Skillstore skill "vet" from https://skillstore.io/skills/imbue-ai-vet.md and its manifest at https://skillstore.io/api/skills/imbue-ai-vet/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Markdown detail GET /skills/imbue-ai-vet.md Signed manifest GET /api/skills/imbue-ai-vet/manifest Signed lockfile GET /api/skills/imbue-ai-vet/lockfile

Test it

Using "vet". A small refactor changes authentication middleware and updates tests.

Expected outcome:

Vet reports that the middleware now skips one error path. The review recommends adding a test for expired tokens before merging.

Using "vet". A Codex session implemented a requested UI change across several files.

Expected outcome:

Vet compares the conversation request with the diff and notes that mobile spacing was not handled. It suggests checking the narrow viewport.

Using "vet". A large branch includes work from another agent and the current task.

Expected outcome:

Vet flags issues from the full diff and separates items that appear unrelated to the current session for human triage.

Security Audit

High Risk

v4 • 7/5/2026 Open versioned report

The skill intentionally runs local vet commands and optional history-loader scripts that read assistant conversation files under hidden home directories. Many markdown backtick detections are false positives, but the documented command execution and transcript access are real privacy and execution risks. No prompt injection language or direct network exfiltration code was found in the reviewed files.

Files scanned

269

Lines analyzed

Review items

False positives ignored

Confirmed security concerns (3)

High

SKILL.md:10 SKILL.md:33-43 SKILL.md:55-62

Sensitive Conversation History Exposure

The skill is designed to review conversation history along with git diffs. The documented history loaders and session discovery steps can expose prompts, assistant replies, code, file paths, and secrets to vet processing.

The documentation explicitly says vet reviews conversation history and gives loader commands for OpenCode, Codex, and Claude Code. The listed hidden session paths are known places where sensitive transcripts are stored.

Medium

SKILL.md:3 SKILL.md:8

Autonomous Tool Execution Pressure

The skill tells agents to run vet immediately after each logical unit of code changes and not wait to be asked. This can lead to unrequested command execution, especially when combined with history-loader guidance.

The instruction is repeated in the front matter and main text. It is not malicious by itself, but it creates consent risk for commands that inspect local data.

Medium

scripts/export_opencode_session.py:8-12 scripts/export_opencode_session.py:32-34

Unvalidated Session Identifier Used in File Paths

The OpenCode exporter uses the supplied session id to build a filesystem path before validating the expected ses_ format. A malformed value could cause unintended directory traversal behavior in local file reads.

The path is directly derived from user input and message ids without visible normalization or validation. Exploitability is limited because the script expects OpenCode-shaped local JSON, so confidence is medium.

Capability review items (19)

These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.

High

SKILL.md:33

Hidden file in home directory

vet "goal" --history-loader "python ~/.agents/skills/vet/scripts/export_opencode_session.py --sessio

The OpenCode command runs a Python script from a hidden home directory path. It is part of the intended setup, but hidden home access is a real privacy and integrity risk.

High

SKILL.md:38

Hidden file in home directory

vet "goal" --history-loader "python ~/.codex/skills/vet/scripts/export_codex_session.py --session-fi

The Codex command references a hidden ~/.codex skill path and takes a session file. This can expose local assistant conversation history.

High

SKILL.md:43

Hidden file in home directory

vet "goal" --history-loader "python ~/.claude/skills/vet/scripts/export_claude_code_session.py --ses

The Claude Code command references a hidden ~/.claude skill path and a session file. This is intended but still sensitive hidden-home access.

High

SKILL.md:55

Hidden file in home directory

2. Run: `grep -rl "UNIQUE_MESSAGE" ~/.local/share/opencode/storage/part/` to find the matching part

The grep command searches ~/.local/share/opencode storage for conversation text. That directory can contain sensitive local session history.

High

SKILL.md:60

Hidden file in home directory

**Codex:** Session files are stored in `~/.codex/sessions/YYYY/MM/DD/`. Find the correct conversatio

The guidance directs users to inspect ~/.codex/sessions for the correct conversation. Codex session files can contain prompts, code, and secrets.

High

SKILL.md:62

Hidden file in home directory

**Claude Code:** Session files are stored in `~/.claude/projects/<encoded-path>/`. The encoded path

The guidance directs users to inspect ~/.claude/projects for conversation files. Those hidden files may contain sensitive project and prompt data.

Medium

SKILL.md:16-25

Ruby/shell backtick execution

```bash

The fenced block instructs users to run pip, uv, and vet commands. Installing and executing a package is a real external command risk, even though the markdown fence itself is benign.

Medium

SKILL.md:32-34

Ruby/shell backtick execution

```bash

The OpenCode example runs the vet CLI and a Python history-loader script. That is intentional external command execution with local data access.

Medium

SKILL.md:37-39

Ruby/shell backtick execution

```bash

The Codex example runs vet with a Python history-loader script. This is external command execution that can process local session files.

Medium

SKILL.md:42-44

Ruby/shell backtick execution

```bash

The Claude Code example runs vet with a Python history-loader script. This is a real external command path that can read local conversation history.

Medium

SKILL.md:47-49

Ruby/shell backtick execution

```bash

The example instructs running the vet CLI. Even without history loading, it executes a local command over repository state.

Medium

SKILL.md:55-57

Ruby/shell backtick execution

2. Run: `grep -rl "UNIQUE_MESSAGE" ~/.local/share/opencode/storage/part/` to find the matching part

The instruction uses grep over OpenCode storage to locate a session. This is external command execution against local application data.

Medium

SKILL.md:77-78

Ruby/shell backtick execution

- `--agentic`: Mode that routes analysis through the locally installed Claude Code or Codex CLI inst

The --agentic option states that vet routes analysis through local Claude Code or Codex CLIs. That mode can invoke external local tools, although only when selected.

Medium

SKILL.md:33

Hidden file access

vet "goal" --history-loader "python ~/.agents/skills/vet/scripts/export_opencode_session.py --sessio

The OpenCode example executes a loader from a hidden home directory. This hidden-file access is expected for the skill but should be consent-gated.

Medium

SKILL.md:38

Hidden file access

vet "goal" --history-loader "python ~/.codex/skills/vet/scripts/export_codex_session.py --session-fi

The Codex example uses a hidden ~/.codex path and a session file. Access to that data is privacy-sensitive even when used for code review.

Medium

SKILL.md:43

Hidden file access

vet "goal" --history-loader "python ~/.claude/skills/vet/scripts/export_claude_code_session.py --ses

The Claude Code example uses a hidden ~/.claude path and session file. The access is intentional but sensitive.

Medium

SKILL.md:55

Hidden file access

2. Run: `grep -rl "UNIQUE_MESSAGE" ~/.local/share/opencode/storage/part/` to find the matching part

The command searches hidden OpenCode storage for a unique message. That is direct access to local conversation data.

Medium

SKILL.md:60

Hidden file access

**Codex:** Session files are stored in `~/.codex/sessions/YYYY/MM/DD/`. Find the correct conversatio

The guidance instructs locating files under ~/.codex/sessions. This is hidden-file access to assistant transcripts.

Medium

SKILL.md:62

Hidden file access

**Claude Code:** Session files are stored in `~/.claude/projects/<encoded-path>/`. The encoded path

The guidance instructs locating files under ~/.claude/projects. This is hidden-file access to assistant transcripts.

Audited by: codex View Audit History →

Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report

Copy report link

https://skillstore.io/skills/imbue-ai-vet/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/imbue-ai-vet/security.svg)](https://skillstore.io/skills/imbue-ai-vet?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/imbue-ai-vet?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/imbue-ai-vet/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/imbue-ai-vet.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>

Academic citations (APA · BibTeX · CFF)

APA citation

imbue-ai. (2026). vet security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/imbue-ai-vet/audits/4

BibTeX citation

@techreport{imbue-ai-imbue-ai-vet-2026,
  author = {imbue-ai},
  title = {vet security audit report (audit version 4)},
  institution = {Skillstore},
  year = {2026},
  number = {4},
  url = {https://skillstore.io/skills/imbue-ai-vet/audits/4},
  note = {Author version unspecified}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "vet security audit report (audit version 4)"
version: "unspecified"
type: report
authors:
  - name: "imbue-ai"
date-released: "2026-07-05"
url: "https://skillstore.io/skills/imbue-ai-vet/audits/4"
identifiers:
  - type: other
    value: "skillstore:imbue-ai-vet:audit:4"
    description: "Skillstore immutable audit report identifier"

Skillstore Score

Why this score Evidence Confidence: Medium

Architecture

Maintainability

Content

Community

Spec Compliance

What You Can Build

Check Agent Code Changes

Run vet after each focused implementation step to catch missed requirements or regression risks.

Review Diff Against Intent

Use conversation history with a git diff to compare what was requested with what was changed.

Standardize Review Output

Use output and threshold options to create consistent findings for pull requests or local review.

Try These Prompts

Run Basic Vet Review

Run vet on the current git diff without conversation history. Summarize any issues and mention whether tests are still needed.

Review With Session Context

Run vet with the correct session history for this conversation. Check whether the implementation matches the user request and list only actionable issues.

Tune Review Strictness

Run vet with a chosen base commit and confidence threshold. Explain which findings are high confidence and which require human judgment.

Prepare Pull Request Findings

Run vet with a pull request friendly output format. Convert the results into a concise review summary with risks, evidence, and suggested fixes.

Best Practices

Run vet after small, logical changes so findings stay focused.
Ask for consent before loading conversation history from hidden directories.
Treat vet as an extra review layer, then run the project tests.

Avoid

Do not run history loaders on private sessions without user approval.
Do not ignore findings solely because the change came from another session.
Do not use vet results as a substitute for compiling, testing, or manual review.

Frequently Asked Questions

What does this skill do?

It guides an agent to run the vet CLI after code changes and review the resulting findings.

Does it need conversation history?

No. Vet can run without history, but history can help compare the implementation with the request.

Which tools does it support?

The instructions include examples for OpenCode, Codex, and Claude Code session history.

Can it read sensitive files?

Yes. History-loader workflows can read hidden session directories that may contain sensitive prompts and code.

Does vet replace tests?

No. The skill states that vet is not a replacement for running tests.

Who should use it?

It is most useful for developers and agent operators who want frequent review of code diffs.

Developer Details

Author

imbue-ai

License

MIT

Skillstore revision

Version notice

The author did not declare a version.

Repository

https://github.com/imbue-ai/vet/tree/main/skills/vet

Ref

30c73eac2afe762f6aa9c4553158769369d47351

Maintenance freshness

7/21/2026

Usage

4 downloads · 104 views

File structure

📁 scripts/

📄 export_claude_code_session.py

📄 export_codex_session.py

📄 export_opencode_session.py

📄 SKILL.md

vet

Install with my Agent

Agent-readable resources

Test it

Security Audit

Confirmed security concerns (3)

Risk Factors

Copy report link

Markdown badge

HTML badge

Embed card

APA citation

BibTeX citation

CITATION.cff

Skillstore Score

What You Can Build

Check Agent Code Changes

Review Diff Against Intent

Standardize Review Output

Try These Prompts

Best Practices

Avoid

Frequently Asked Questions

Developer Details