Grades are a hygiene check, not a security guarantee.

Claude Code, Skill

Mc Agent Toolkit

Monte Carlo's official toolkit for AI coding agents.

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 f1ea90fa2b7f, unchanged since the check below.

PERMISSION_DELETE_FILES NETWORK_NO_FIXED_HOST NETWORK_UNNAMED_HOST SECRETS_PATH_DOTENV SECRETS_ENV_READ OBFUSCATION_FILE_CAP_REACHED

Why this grade

  • PERMISSION_DELETE_FILES Low

    Contains a call that can delete files.

    plugins/claude-code/hooks/prevent/lib/cache.py, line 155 os.remove(path)

  • NETWORK_NO_FIXED_HOST Low

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

    plugins/claude-code/hooks/telemetry/lib/install-beacon.sh, line 75 # MC_BEACON_SYNC (test-only) runs curl in the foreground so tests can assert

  • NETWORK_UNNAMED_HOST Low

    Calls a fixed host that the description does not name.

    plugins/claude-code/hooks/telemetry/lib/install-beacon.sh, line 75 # MC_BEACON_SYNC (test-only) runs curl in the foreground so tests can assert

  • SECRETS_PATH_DOTENV Low

    Mentions a .env file.

    plugins/claude-code/evals/constants.py, line 13 load_dotenv(EVALS_DIR / ".env")

  • SECRETS_ENV_READ Note

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

    plugins/claude-code/evals/constants.py, line 27 mcd_token = os.environ.get("MCD_TOKEN")

  • OBFUSCATION_FILE_CAP_REACHED Note

    The 400 file cap was reached before every file was read.

    skills/push-ingestion/scripts/templates/bigquery-iceberg/collect_and_push_metadata.py, 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

    plugins/claude-code/hooks/prevent/lib/cache.py, line 155

    os.remove(path)

    plugins/claude-code/hooks/prevent/lib/cache.py, line 185

    os.remove(path)

    plugins/claude-code/hooks/prevent/lib/cache.py, line 214

    os.remove(path)

    Show more

    plugins/claude-code/hooks/prevent/lib/cache.py, line 368

    os.remove(filepath)

    plugins/claude-code/hooks/prevent/lib/protocol.py, line 208

    result = subprocess.run(

    plugins/codex/hooks/prevent/lib/cache.py, line 155

    os.remove(path)

    plugins/codex/hooks/prevent/lib/cache.py, line 185

    os.remove(path)

    plugins/codex/hooks/prevent/lib/cache.py, line 214

    os.remove(path)

    plugins/codex/hooks/prevent/lib/cache.py, line 368

    os.remove(filepath)

    plugins/codex/hooks/prevent/lib/protocol.py, line 208

    result = subprocess.run(

    plugins/copilot/hooks/prevent/lib/protocol.py, line 208

    result = subprocess.run(

    plugins/cortex-code/hooks/prevent/lib/protocol.py, line 208

    result = subprocess.run(

    plugins/cursor/hooks/prevent/lib/protocol.py, line 208

    result = subprocess.run(

    plugins/shared/prevent/lib/protocol.py, line 208

    result = subprocess.run(

    skills/generate-validation-notebook/scripts/generate_notebook_url.py, line 137

    subprocess.run(["open", url])

    plugins/opencode/README.md, line 138

    | Git staged files | `subprocess.run(["git", ...])` | `Bun.spawn(["git", ...])` |

  • 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 clidocs.getmontecarlo.com. The description does not name that host. can reach api.getmontecarlo.com. The description does not name that host.

    NETWORK_NO_FIXED_HOST NETWORK_UNNAMED_HOST

    plugins/claude-code/hooks/telemetry/lib/install-beacon.sh, line 75

    # MC_BEACON_SYNC (test-only) runs curl in the foreground so tests can assert

    plugins/claude-code/hooks/telemetry/lib/install-beacon.sh, line 78

    curl -fsS -m 2 -X POST -H 'Content-Type: application/json' -d "$PAYLOAD" "$BEACON_URL" >/dev/null 2>&1 || true

    plugins/claude-code/hooks/telemetry/lib/install-beacon.sh, line 80

    ( curl -fsS -m 2 -X POST \

    Show more

    plugins/claude-code/hooks/telemetry/scripts/skill-beacon.sh, line 60

    ( curl -fsS -m 2 -X POST \

    plugins/codex/hooks/telemetry/lib/install-beacon.sh, line 75

    # MC_BEACON_SYNC (test-only) runs curl in the foreground so tests can assert

    plugins/codex/hooks/telemetry/lib/install-beacon.sh, line 78

    curl -fsS -m 2 -X POST -H 'Content-Type: application/json' -d "$PAYLOAD" "$BEACON_URL" >/dev/null 2>&1 || true

    plugins/codex/hooks/telemetry/lib/install-beacon.sh, line 80

    ( curl -fsS -m 2 -X POST \

    plugins/copilot/hooks/telemetry/lib/install-beacon.sh, line 75

    # MC_BEACON_SYNC (test-only) runs curl in the foreground so tests can assert

    skills/prevent/references/TROUBLESHOOTING.md, line 6

    curl -s -o /dev/null -w "%{http_code}" https://mcp.getmontecarlo.com/mcp/toolkit

    skills/push-ingestion/references/direct-http-api.md, line 39

    curl -X POST "https://integrations.getmontecarlo.com/ingest/v1/metadata" \

    skills/push-ingestion/references/direct-http-api.md, line 83

    curl -X POST "https://integrations.getmontecarlo.com/ingest/v1/lineage" \

    skills/push-ingestion/references/direct-http-api.md, line 120

    curl -X POST "https://integrations.getmontecarlo.com/ingest/v1/lineage" \

    skills/push-ingestion/references/direct-http-api.md, line 167

    curl -X POST "https://integrations.getmontecarlo.com/ingest/v1/querylogs" \

  • Secrets

    Concern

    reads a credential or environment file.

    SECRETS_ENV_READ SECRETS_PATH_DOTENV

    plugins/claude-code/evals/constants.py, line 13

    load_dotenv(EVALS_DIR / ".env")

    plugins/claude-code/evals/constants.py, line 27

    mcd_token = os.environ.get("MCD_TOKEN")

    plugins/claude-code/evals/constants.py, line 33

    mcd_token = os.environ.get("MCD_TOKEN_DEV")

    Show more

    skills/connection-auth-rules/fetch_schema.py, line 36

    token = os.environ.get("GITHUB_TOKEN")

    skills/instrument-agent/references/setup-template.md, line 96

    api_token = os.environ.get("MCD_DEFAULT_API_TOKEN")

    skills/instrument-agent/references/setup-template.md, line 336

    assert os.environ.get("MCD_DEFAULT_API_TOKEN"), (

    skills/instrument-agent/references/workflow.md, line 205

    bool(os.environ.get("MCD_DEFAULT_API_ID")) and bool(os.environ.get("MCD_DEFAULT_API_TOKEN"))

    skills/onboarding/reference/output-modes.md, line 860

    creds = select(candidates, os.environ.get("MCD_CREDENTIALS_ID"), "credentials")

    skills/push-ingestion/scripts/sample_verify.py, line 302

    parser.add_argument("--key-token", default=os.environ.get("MCD_TOKEN"))

    .gitignore, line 1

    .env

    plugins/claude-code/evals/.gitignore, line 1

    .venv/

    plugins/claude-code/evals/README.md, line 15

    cp .env.example .env

    plugins/claude-code/evals/README.md, line 16

    # edit .env with your keys

    skills/instrument-agent/SKILL.md, line 34

    - **Env files** - `.env`, `.envrc`, shell rc files. Always propose the change and wait for confirmation before editing.

    skills/instrument-agent/references/redaction.md, line 257

    (e.g., `.env.example`, deployment manifest, or the `mc.setup()` module

    skills/instrument-agent/references/setup-template.md, line 374

    - Env files (`.env`, `.env.example`, deployment manifests).

  • Agent instructions

    Pass

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

  • Obfuscation

    Note

    the file cap was reached before every file was read.

    OBFUSCATION_FILE_CAP_REACHED

    skills/push-ingestion/scripts/templates/bigquery-iceberg/collect_and_push_metadata.py, line 1

    """

  • Licence

    Pass

    A licence file is present (LICENSE).

  • Maintainer activity

    Pass

    The latest commit is within the last 365 days.

Note

Hygiene check of commit f1ea90fa2b7f. can delete files. can reach a host that is not written as a fixed address. can reach clidocs.getmontecarlo.com. The description does not name that host. can reach api.getmontecarlo.com. The description does not name that host. reads a credential or environment file. the file cap was reached before every file was read.

Date and source

Date checked:

View source

github.com

Commit graded: f1ea90fa2b7fa1ece98e52a45d887c609f2a8de6

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