Grades are a hygiene check, not a security guarantee.

MCP, MCP server

AgentShield

AgentShield, an MCP server listed in the PlugVet directory.

Compatibility: Not stated.

Grade D

Two or more Medium findings, or a High. Only try it in a sandbox.

Graded by PlugVetRubric v2

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

INSTALL_REMOTE_SCRIPT SECRETS_PATH_CREDENTIAL

Why this grade

  • INSTALL_REMOTE_SCRIPT Medium

    Fetches a script from the network and runs it (a pipe to a shell, or an install hook with a URL).

    scripts/container_install_deps.sh, line 236 curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y --no-modify-path

  • SECRETS_PATH_CREDENTIAL Medium

    Mentions a credential store path (~/.ssh, id_rsa, .npmrc, .aws/credentials, credentials.json, .netrc).

    .gitignore, line 37 credentials.json

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.

If you think this grade is wrong, email [email protected] with the entry link and your evidence. We aim to acknowledge within two working days and decide within seven. If we confirm an error, we aim to correct it within 24 hours of confirming it. These are aims, not guarantees.

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

    Note

    requests shell access. The manifest names this permission.

    PERMISSION_SHELL_DECLARED

    src/agentshield/core/doctor.py, line 351

    proc = subprocess.run(

    src/agentshield/enforce/execve.py, line 137

    proc = subprocess.run(cmd, capture_output=True, text=True)

    src/agentshield/guard/shell_wrapper.py, line 211

    result = subprocess.run([shell, "--rcfile", init_file])

    Show more

    src/agentshield/guard/shell_wrapper.py, line 222

    result = subprocess.run([shell], env=env)

    src/agentshield/guard/shell_wrapper.py, line 230

    result = subprocess.run([shell, "--init-command", Path(init_file).read_text()])

    src/agentshield/protect/probes.py, line 248

    proc = subprocess.run(

    src/agentshield/analyzers/rules/T3_1_shell_exec.yaml, line 4

    - pattern: subprocess.call(...)

    src/agentshield/analyzers/rules/T3_1_shell_exec.yaml, line 5

    message: "T3.1: Shell execution via subprocess.call() detected at install time"

  • Install and update

    Serious

    install fetches a script from the network.

    INSTALL_REMOTE_SCRIPT

    scripts/container_install_deps.sh, line 236

    curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y --no-modify-path

    scripts/container_install_deps.sh, line 242

    curl -LsSf https://astral.sh/uv/install.sh | sh

    scripts/container_install_deps.sh, line 288

    if curl -fsSL https://bun.sh/install | bash >/dev/null 2>&1; then

  • Network

    Concern

    can reach a host that is not written as a fixed address. can reach micro.mamba.pm. The description does not name that host.

    NETWORK_NO_FIXED_HOST NETWORK_UNNAMED_HOST

    scripts/container_install_deps.sh, line 163

    apk) echo "git curl ca-certificates tar unzip xz bash" ;;

    scripts/container_install_deps.sh, line 164

    apt-get) echo "git curl ca-certificates tar unzip xz-utils" ;;

    scripts/container_install_deps.sh, line 165

    dnf|yum) echo "git curl ca-certificates tar unzip xz" ;;

    Show more

    scripts/container_install_deps.sh, line 166

    pacman) echo "git curl ca-certificates tar unzip xz" ;;

    scripts/container_install_deps.sh, line 167

    zypper) echo "git curl ca-certificates tar unzip xz" ;;

    scripts/container_install_deps.sh, line 313

    if curl -Ls "https://micro.mamba.pm/api/micromamba/$MM_ARCH/latest" | tar -xj -C "$HOME" bin/micromamba >/dev/null 2>&1; then

    src/agentshield/core/audit_forward.py, line 124

    with socket.create_connection(addr, timeout=config.timeout_seconds) as sock:

    src/agentshield/core/doctor.py, line 267

    with socket.create_connection((host, port), timeout=1):

  • Secrets

    Concern

    reads a credential or environment file.

    SECRETS_ENV_READ SECRETS_PATH_CREDENTIAL SECRETS_PATH_DOTENV

    src/agentshield/analyzers/npm_deep.py, line 62

    _ENV_RE = re.compile(r"process\.env")

    src/agentshield/core/config.py, line 271

    env = os.environ.get("NVD_API_KEY")

    .gitignore, line 37

    credentials.json

    Show more

    src/agentshield/core/config.py, line 275

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

    .gitignore, line 32

    # ── Secrets and credentials ──────────────────────────────────────────────────

    .gitignore, line 33

    .env

    .gitignore, line 35

    *.env

    src/agentshield/reports/templates/posture_report.html.jinja2, line 123

    .env-chip {

  • 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 c994c8421a49. requests shell access. The manifest names this permission. install fetches a script from the network. can reach a host that is not written as a fixed address. can reach micro.mamba.pm. The description does not name that host. reads a credential or environment file.

Date and source

Date checked:

View source

github.com

Commit graded: c994c8421a498dcd5daf2ca66740b160be66513d

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