Grades are a hygiene check, not a security guarantee.

MCP, MCP server

Ai Surface

Ai Surface, an MCP server listed in the PlugVet directory.

Compatibility: Not stated.

Grade C

One Medium finding. Read the findings 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 7e57dc930fb2, unchanged since the check below.

PERMISSION_SHELL_UNDECLARED

Why this grade

  • PERMISSION_SHELL_UNDECLARED Medium

    Runs shell commands that the manifest or description does not mention.

    src/ai_surface/repo.py, line 145 shutil.rmtree(tmp, ignore_errors=True)

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. requests shell access. No manifest field names shell or command execution.

    PERMISSION_SHELL_UNDECLARED PERMISSION_DELETE_FILES

    src/ai_surface/repo.py, line 145

    shutil.rmtree(tmp, ignore_errors=True)

    src/ai_surface/repo.py, line 148

    subprocess.run(

    src/ai_surface/data/mcp/allowlist_bypass_binaries.py, line 18

    "python": "-c '<code>' executes arbitrary Python, including os.system()/subprocess calls",

    Show more

    src/ai_surface/data/mcp/allowlist_bypass_binaries.py, line 19

    "python3": "-c '<code>' executes arbitrary Python, including os.system()/subprocess calls",

    src/ai_surface/integrations/claude_code_hook.py, line 39

    proc = subprocess.run(

    .github/action/entry.py, line 86

    return subprocess.run(

    .github/action/entry.py, line 96

    return subprocess.run(

    .github/action/entry.py, line 188

    subprocess.run(

  • 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.

    NETWORK_NO_FIXED_HOST

    src/ai_surface/ui_server.py, line 4

    report.json, over http://localhost so the UI's `fetch("./report.json")` works

    src/ai_surface/ui/app.js, line 7

    * Network calls allowed: fetch("./report.json") and POST "/api/scan". Scanning

    src/ai_surface/ui/app.js, line 157

    the page can <span class="mono">fetch("./report.json")</span> (opening via

    Show more

    src/ai_surface/ui/app.js, line 240

    fetch("./report.json", { cache: "no-store" })

    src/ai_surface/ui/app.js, line 264

    fetch("/api/scan", {

    .github/action/entry.py, line 194

    # Defensive fetch (fetch-depth: 0 in the consumer workflow makes this a no-op).

    .github/action/entry.py, line 284

    resp = requests.get(url, headers=headers, timeout=15)

    .github/action/entry.py, line 301

    resp = requests.patch(url, headers=headers, json={"body": marker_body}, timeout=15)

    .github/action/entry.py, line 308

    resp = requests.post(url, headers=headers, json={"body": marker_body}, timeout=15)

  • Secrets

    Concern

    reads a credential or environment file.

    SECRETS_PATH_DOTENV

    fixtures/generate_demo.py, line 209

    Finding(surface="AI provider keys (.env)", category=CATEGORY_ENV_KEY,

    fixtures/generate_demo.py, line 210

    evidence=_ev([".env.example"], "OPENAI_API_KEY=\nANTHROPIC_API_KEY=\nLANGCHAIN_API_KEY=",

    fixtures/generate_demo.py, line 214

    Finding(surface="Observability key (.env)", category=CATEGORY_ENV_KEY,

    Show more

    fixtures/generate_demo.py, line 215

    evidence=_ev([".env.example"], "LANGSMITH_API_KEY=", {"keys": ["LANGSMITH_API_KEY"]}),

    src/ai_surface/observability.py, line 131

    return name == ".envrc" or name == ".env" or name.startswith(".env.") or name.endswith(".env")

    src/ai_surface/detectors/env_keys.py, line 12

    * exact filename: ``.env``, ``.envrc``, ``env.example``

    src/ai_surface/detectors/env_keys.py, line 13

    * glob match: ``.env.*`` (e.g. ``.env.production``, ``.env.local``)

    src/ai_surface/detectors/env_keys.py, line 14

    * glob match: ``*.env`` (e.g. ``staging.env``)

  • Agent instructions

    Pass

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

  • Obfuscation

    Pass

    No encoded or minified payload found.

  • 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 7e57dc930fb2. can delete files. requests shell access. No manifest field names shell or command execution. can reach a host that is not written as a fixed address. reads a credential or environment file.

Date and source

Date checked:

View source

github.com

Commit graded: 7e57dc930fb2b0f9fc2f5b878809b12efcc83864

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