Grades are a hygiene check, not a security guarantee.

MCP, MCP server

io.github.basicmachines-co/basic-memory

io.github.basicmachines-co/basic-memory, 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.

PERMISSION_SHELL_UNDECLARED

Why this grade

  • PERMISSION_SHELL_UNDECLARED Medium

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

    .agents/skills/pythonic-code/scripts/run_evals.py, line 272 result = subprocess.run(

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

    requests shell access. No manifest field names shell or command execution. can delete files.

    PERMISSION_SHELL_UNDECLARED PERMISSION_DELETE_FILES

    .agents/skills/pythonic-code/scripts/run_evals.py, line 272

    result = subprocess.run(

    benchmarks/scripts/read_load_bench.py, line 133

    result = subprocess.run(

    benchmarks/scripts/read_load_bench.py, line 164

    result = subprocess.run(

    Show more

    benchmarks/scripts/read_load_bench.py, line 690

    shutil.rmtree(path)

    benchmarks/scripts/write_load_bench.py, line 275

    shutil.rmtree(path)

    benchmarks/src/basic_memory_benchmarks/cli.py, line 842

    shutil.rmtree(target)

    benchmarks/src/basic_memory_benchmarks/utils.py, line 35

    return subprocess.run(args, cwd=cwd, text=True, capture_output=True, check=check, env=env)

    benchmarks/src/basic_memory_benchmarks/converters/xafs_to_corpus.py, line 157

    shutil.rmtree(docs_dir)

  • Install and update

    Note

    README documents an installer that pipes a download into a shell. The docs document an installer that pipes a download into a shell.

    INSTALL_DOCUMENTED_INSTALLER

    integrations/openclaw/README.md, line 49

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

    integrations/openclaw/index.ts, line 137

    "Install uv first (brew install uv, or curl -LsSf https://astral.sh/uv/install.sh | sh), " +

    integrations/openclaw/scripts/setup-bm.sh, line 13

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

    Show more

    plugins/claude-code/README.md, line 74

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

    plugins/codex/README.md, line 94

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

    src/basic_memory/cli/commands/hook.py, line 1556

    return "brew install uv (or: curl -LsSf https://astral.sh/uv/install.sh | sh)"

    src/basic_memory/cli/commands/hook.py, line 1557

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

  • Network

    Concern

    can reach a host that is not written as a fixed address.

    NETWORK_NO_FIXED_HOST

    .agents/skills/instrumentation/references/javascript/frameworks.md, line 31

    async fetch(request: Request, env: Env, ctx: ExecutionContext) {

    benchmarks/src/basic_memory_benchmarks/datasets/locomo.py, line 20

    response = httpx.get(url, timeout=120)

    benchmarks/src/basic_memory_benchmarks/datasets/locomo_audit.py, line 52

    response = httpx.get(_errors_url(conversation_index, sha), timeout=120)

    Show more

    benchmarks/src/basic_memory_benchmarks/llm/runners.py, line 201

    response = httpx.post(

    benchmarks/src/basic_memory_benchmarks/llm/tool_agent.py, line 369

    response = httpx.post(

    CHANGELOG.md, line 2948

    - **#305**: ChatGPT tools for search and fetch

    benchmarks/README.md, line 120

    just bench-prepare-longmemeval # fetch (~278MB) + convert all 500

    src/basic_memory/ci/project_updates.py, line 286

    with urllib.request.urlopen(request, timeout=20) as response:

  • Secrets

    Concern

    reads a credential or environment file.

    SECRETS_ENV_READ SECRETS_PATH_DOTENV

    .agents/skills/instrumentation/references/javascript/patterns.md, line 71

    token: process.env.LOGFIRE_TOKEN,

    benchmarks/src/basic_memory_benchmarks/llm/runners.py, line 249

    resolved_api_key = api_key if api_key is not None else os.getenv("OPENAI_API_KEY")

    benchmarks/src/basic_memory_benchmarks/llm/tool_agent.py, line 587

    resolved_api_key = api_key if api_key is not None else os.getenv("OPENAI_API_KEY")

    Show more

    benchmarks/src/basic_memory_benchmarks/providers/mem0_local.py, line 46

    api_key = os.getenv("MEM0_OPENAI_COMPAT_API_KEY", "local")

    benchmarks/src/basic_memory_benchmarks/providers/mem0_local.py, line 101

    elif os.getenv("OPENAI_API_KEY"):

    benchmarks/src/basic_memory_benchmarks/providers/supermemory_local.py, line 56

    api_key = os.getenv("SUPERMEMORY_API_KEY")

    integrations/openclaw/bm-client.ts, line 321

    if (options?.env) {

    .agents/skills/instrumentation/references/javascript/frameworks.md, line 49

    Set environment variables in `.env.local` or Vercel dashboard:

    .dockerignore, line 32

    venv/

    .env.example, line 2

    # Copy this file to .env and customize as needed

    .env.example, line 3

    # Note: .env files are gitignored and should never be committed

    .gitignore, line 31

    # Virtual environments

    AGENTS.md, line 479

    - Removed .env file loading for improved security

    CHANGELOG.md, line 2881

    - **#330**: Remove .env file loading from BasicMemoryConfig

  • 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. the file cap was reached before every file was read.

    OBFUSCATION_FILE_OVER_READ_CAP OBFUSCATION_FILE_CAP_REACHED

    .test_durations, line 1

    {

    CHANGELOG.md, line 1

    # CHANGELOG

    uv.lock, line 1

    version = 1

    Show more

    benchmarks/uv.lock, line 1

    version = 1

    integrations/shared/schemas/session.md, 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 976a10c89773. requests shell access. No manifest field names shell or command execution. can delete files. README documents an installer that pipes a download into a shell. The docs document an installer that pipes a download into a shell. can reach a host that is not written as a fixed address. reads a credential or environment file. a file was over the read cap and was not fully read. the file cap was reached before every file was read.

Date and source

Date checked:

View source

github.com

Commit graded: 976a10c8977345e1f84b9d1a1557a0e2d0bad540

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