Grades are a hygiene check, not a security guarantee.

Claude Code, Skill

skillmem

Procedural memory for Claude Code: not facts about you, but how a task was solved — trigger, steps, outcome, lessons.

Compatibility: Not stated.

Grade D

Two or more Medium findings, or a High finding. 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.

Rescanned at commit 491e2b1169ad, unchanged since the check below.

INSTALL_REMOTE_SCRIPT AGENT_IGNORE_INSTRUCTIONS

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).

    install.sh, line 6 # curl -sSL https://<your-host>/skillmem/install.sh | bash

  • AGENT_IGNORE_INSTRUCTIONS Medium

    Text tells the agent to ignore earlier instructions.

    docs/TZ-provenance-trust.md, line 83 1. kind='feedback' И origin='derived', тело «IGNORE ALL PREVIOUS INSTRUCTIONS…»

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

    Concern

    can delete files.

    PERMISSION_DELETE_FILES

    scripts/docker_smoke.sh, line 28

    proc = subprocess.Popen(command, stdin=subprocess.PIPE, stdout=subprocess.PIPE,

    scripts/docker_smoke.sh, line 72

    subprocess.run(["docker", "rm", "-f", "-v", name],

    scripts/gate_new_tests.py, line 82

    return subprocess.run(["git", *args], check=True, capture_output=True).stdout

    Show more

    scripts/gate_new_tests.py, line 154

    shutil.rmtree(tree / "tests", ignore_errors=True)

    scripts/gate_new_tests.py, line 165

    proc = subprocess.Popen(

    scripts/gate_new_tests.py, line 174

    subprocess.run(["taskkill", "/F", "/T", "/PID", str(proc.pid)],

    scripts/gate_new_tests.py, line 180

    shutil.rmtree(tree)

    scripts/mcp_smoke.py, line 32

    def _send(proc: subprocess.Popen, payload: dict) -> None:

    scripts/mcp_smoke.py, line 39

    def _read(proc: subprocess.Popen, timeout: float = float(os.environ.get("SMOKE_TIMEOUT", 120))) -> dict:

    scripts/mcp_smoke.py, line 75

    proc = subprocess.Popen(

    skillmem/packs.py, line 320

    shutil.rmtree(tmp, ignore_errors=True)

  • Install and update

    Serious

    install fetches a script from the network.

    INSTALL_REMOTE_SCRIPT

    install.sh, line 6

    # curl -sSL https://<your-host>/skillmem/install.sh | bash

    install.sh, line 7

    # curl -sSL https://<your-host>/skillmem/install.sh | bash -s -- --no-claude-code

    install.sh, line 8

    # curl -sSL https://<your-host>/skillmem/install.sh | bash -s -- --no-semantic

    Show more

    install.sh, line 126

    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

    install.sh, line 147

    curl -sSLf -o "$TMPDIR/pkg.tgz" "$PACKAGE_URL" || \

    install.sh, line 159

    { [ -z "${LOCAL_PKG:-}" ] && curl -sSLf -o "$TMPDIR/pkg.tgz.sha256" "$SHA_URL"; }; then

    skillmem/hooks.py, line 511

    return fetch()

    Show more

    .github/workflows/registry.yml, line 46

    with urllib.request.urlopen(

  • Secrets

    Note

    reads an environment variable.

    SECRETS_ENV_READ

    skillmem/cli.py, line 1618

    tok = os.environ.get("SKILLMEM_GITHUB_TOKEN")

    skillmem/server.py, line 506

    default=Path(os.environ.get("SKILLMEM_TOKENS", _default_tokens_path())))

  • Agent instructions

    Serious

    instructions tell the agent to ignore earlier instructions.

    AGENT_IGNORE_INSTRUCTIONS

    docs/TZ-provenance-trust.md, line 83

    1. kind='feedback' И origin='derived', тело «IGNORE ALL PREVIOUS INSTRUCTIONS…»

  • 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.

Note

Hygiene check of commit 491e2b1169ad. can delete files. install fetches a script from the network. can reach a host that is not written as a fixed address. reads an environment variable. instructions tell the agent to ignore earlier instructions.

Date and source

Date checked:

View source

github.com

Commit graded: 491e2b1169ad430468e082af238dd0a5b046d7ad

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