Grades are a hygiene check, not a security guarantee.

MCP, MCP server

io.github.LumabyteCo/clarifyprompt

A context-aware MCP prompt compiler that transforms vague prompts into platform-optimized prompts for 60+ AI platforms across 7 categories — grounded in your workspace signals (CLAUDE.md, AGENTS.md, .cursorrules, package.json), resolved intent, and the capabilities of the ta

Compatibility: Not stated.

Grade B

Minor issues only, no Medium or High. Worth a quick look at the findings below before installing.

Graded by PlugVetRubric v2

Not a guarantee. A hygiene check of the source at the commit shown, not a security audit.

Rescanned at commit e0c04dd12959, unchanged since the check below.

PERMISSION_DELETE_FILES NETWORK_NO_FIXED_HOST NETWORK_UNNAMED_HOST SECRETS_PATH_DOTENV SECRETS_ENV_READ OBFUSCATION_FILE_OVER_READ_CAP

Why this grade

  • PERMISSION_DELETE_FILES Low

    Contains a call that can delete files.

    evals/matrix.mjs, line 262 await fs.rm(tmpDir, { recursive: true, force: true });

  • NETWORK_NO_FIXED_HOST Low

    Makes a network call whose host is not written as a fixed address.

    evals/dialect-benchmark/run.mjs, line 96 const res = await fetch(`${API_URL}/chat/completions`, {

  • NETWORK_UNNAMED_HOST Low

    Calls a fixed host that the description does not name.

    evals/dialect-benchmark/run.mjs, line 96 const res = await fetch(`${API_URL}/chat/completions`, {

  • SECRETS_PATH_DOTENV Low

    Mentions a .env file.

    .claude/skills/ship-check/SKILL.md, line 195 | 2026-04-24 | **CP-2: server.json env-var declarations match `.env.example`** - caught the gap that drove 1.3.0 → 1.3.1 | project `ADD: CP-2` → user `### 11. MCP server-manifest e

  • SECRETS_ENV_READ Note

    Reads an environment variable whose name contains KEY, SECRET, TOKEN, PASSWORD or CREDENTIAL.

    evals/dialect-benchmark/run.mjs, line 30 const API_KEY = process.env.LLM_API_KEY || '';

  • OBFUSCATION_FILE_OVER_READ_CAP Note

    A file was over the read cap and was not fully read.

    evals/dialect-benchmark/out/dialect-benchmark-2026-10-05-15-13.json, line 1 {

Any High, or two or more Medium findings, give D. One Medium gives C. Low findings or a security Note give B. Each code names a finding behind the letter.

Grades are a hygiene check of the source at the commit shown, on the date checked, not a security audit or a guarantee. The free directory grades are automated. Before release, a PlugVet engineer reviews every paid report and any grade we hold back, including all F grades, against the source code and the evidence we quote.

What was checked

Plain notes from the hygiene checks.

  • Permissions

    Concern

    can delete files.

    PERMISSION_DELETE_FILES

    evals/matrix.mjs, line 262

    await fs.rm(tmpDir, { recursive: true, force: true });

    evals/run.mjs, line 644

    if (ws) fs.rm(ws, { recursive: true, force: true }).catch(() => {});

    evals/run.mjs, line 645

    fs.rm(home, { recursive: true, force: true }).catch(() => {});

  • Install and update

    Pass

    No install-time script found, and dependencies are pinned or absent.

  • Network

    Concern

    can reach a host that is not written as a fixed address. can reach api.tavily.com. The description does not name that host. can reach api.search.brave.com. The description does not name that host. can reach google.serper.dev. The description does not name that host. can reach serpapi.com. The description does not name that host. can reach api.exa.ai. The description does not name that host.

    NETWORK_NO_FIXED_HOST NETWORK_UNNAMED_HOST

    evals/dialect-benchmark/run.mjs, line 96

    const res = await fetch(`${API_URL}/chat/completions`, {

    src/engine/llm/client.ts, line 280

    const response = await fetch(`${this.config.apiUrl}/chat/completions`, {

    src/engine/llm/client.ts, line 331

    const response = await fetch(`${this.config.apiUrl}/messages`, {

    Show more

    src/engine/llm/client.ts, line 390

    const response = await fetch(`${this.config.apiUrl}/chat/completions`, {

    src/engine/llm/model-capabilities.ts, line 64

    const res = await fetch(`${base}/api/show`, {

    src/engine/memory/embeddings.ts, line 66

    const response = await fetch(`${this.apiUrl}/embeddings`, {

    src/engine/memory/packs.ts, line 157

    const response = await fetch(source, { signal: AbortSignal.timeout(15_000) });

    src/engine/search/client.ts, line 76

    const response = await fetch('https://api.tavily.com/search', {

  • Secrets

    Concern

    reads a credential or environment file.

    SECRETS_ENV_READ SECRETS_PATH_DOTENV

    evals/run.mjs, line 71

    ...env,

    evals/dialect-benchmark/run.mjs, line 30

    const API_KEY = process.env.LLM_API_KEY || '';

    .claude/skills/ship-check/SKILL.md, line 195

    | 2026-04-24 | **CP-2: server.json env-var declarations match `.env.example`** - caught the gap that drove 1.3.0 → 1.3.1 | project `ADD: CP-2` → user `### 11. MCP server-manifest e

    Show more

    src/engine/llm/client.ts, line 193

    || process.env.LLM_API_KEY

    src/engine/llm/client.ts, line 194

    || process.env.OLLAMA_API_KEY

    src/engine/memory/embeddings.ts, line 45

    process.env.EMBED_API_KEY ||

    src/engine/memory/embeddings.ts, line 46

    process.env.LLM_API_KEY ||

    src/engine/search/client.ts, line 29

    apiKey: config?.apiKey || process.env.SEARCH_API_KEY || process.env.TAVILY_API_KEY || '',

    .dockerignore, line 9

    # baked even without this file; this is defense-in-depth + a smaller context.)

    .dockerignore, line 10

    .env

    .github/workflows/ci.yml, line 112

    - name: .env must not be committed

    .github/workflows/ci.yml, line 115

    if git ls-files --error-unmatch .env 2>/dev/null; then

    .github/workflows/ci.yml, line 116

    echo "::error::.env is tracked. It must be gitignored."

    .github/workflows/ci.yml, line 119

    echo ".env not tracked ✓"

  • Agent instructions

    Pass

    No instruction to ignore earlier instructions or to hide a step.

  • Obfuscation

    Note

    a file was over the read cap and was not fully read.

    OBFUSCATION_FILE_OVER_READ_CAP

    evals/dialect-benchmark/out/dialect-benchmark-2026-10-05-15-13.json, line 1

    {

    evals/dialect-benchmark/out/dialect-benchmark-grounded-2026-10-05-17-15.json, line 1

    {

    evals/dialect-benchmark/out/final.json, line 1

    {

  • Licence

    Pass

    A licence file is present (LICENSE).

  • Maintainer activity

    Pass

    The latest commit is within the last 365 days.

Get the full report on this tool, £49

Note

Hygiene check of commit e0c04dd12959. can delete files. can reach a host that is not written as a fixed address. can reach api.tavily.com. The description does not name that host. can reach api.search.brave.com. The description does not name that host. can reach google.serper.dev. The description does not name that host. can reach serpapi.com. The description does not name that host. can reach api.exa.ai. The description does not name that host. reads a credential or environment file. a file was over the read cap and was not fully read.

Date and source

Date checked:

View source

github.com

Commit graded: e0c04dd12959adf3c1f8c78d600719b4224fef1b

This link goes to the original host. PlugVet does not host or check what you download from there, and installing it is your own decision and risk.

Read how this letter is chosen