Grades are a hygiene check, not a security guarantee.

Claude Code, Skill

spellbook

Cross-runtime skills for Claude Code, Codex, and multi-agent workflows.

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 ed52af74bce8, unchanged since the check below.

NETWORK_HOST_FROM_INPUT SECRETS_PATH_CREDENTIAL

Why this grade

  • NETWORK_HOST_FROM_INPUT High

    A file takes a URL or endpoint as input and has no fixed host list.

    plugins/idea-coach/skills/idea-to-product/scripts/verify_prototype.py, line 161 "fetch() is forbidden": r"\bfetch\b",

  • SECRETS_PATH_CREDENTIAL Medium

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

    skills/cliproxy-newapi-stack/SKILL.md, line 67 SSH_TARGET=root@<HOST> SSH_KEY=~/.ssh/id_ed25519 PORT=8200 \

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

    skills/build-product-demo/scripts/analyze_demo_pacing.py, line 59

    result = subprocess.run(command, capture_output=True, text=True)

    skills/build-product-demo/scripts/probe_demo_media.py, line 82

    result = subprocess.run(command, check=True, capture_output=True, text=True)

    skills/cliproxy-newapi-stack/scripts/set_pricing.py, line 37

    result = subprocess.run(cmd, capture_output=True, text=True, check=False)

    Show more

    skills/cliproxy-newapi-stack/scripts/topup.sh, line 60

    subprocess.run(

    skills/codebase-audit/evals/fixture/app/storage.py, line 31

    os.remove(tmp)

    skills/codex/scripts/run_with_timeout.py, line 26

    result = subprocess.run(

    skills/codex/scripts/run_with_timeout.py, line 53

    def stop_process_group(process: subprocess.Popen[bytes]) -> None:

    skills/codex/scripts/run_with_timeout.py, line 80

    process = subprocess.Popen(args.command, start_new_session=True)

    skills/ip-check/scripts/ipcheck.py, line 435

    r = subprocess.run(["dig", "+short", "-x", ip], capture_output=True, text=True, timeout=10)

  • 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

    README.md, line 54

    curl -fsSL https://raw.githubusercontent.com/majiayu000/spellbook/main/install.sh | bash -s -- --target all

    README_CN.md, line 52

    curl -fsSL https://raw.githubusercontent.com/majiayu000/spellbook/main/install.sh | bash -s -- --target all

    docs/installation.md, line 40

    curl -fsSL https://raw.githubusercontent.com/majiayu000/spellbook/main/install.sh | bash -s -- --target all

    Show more

    docs/installation.md, line 43

    curl -fsSL https://raw.githubusercontent.com/majiayu000/spellbook/main/install.sh | bash -s -- --target claude

    docs/installation.md, line 46

    curl -fsSL https://raw.githubusercontent.com/majiayu000/spellbook/main/install.sh | bash -s -- --target codex

    docs/migration-from-claude-arsenal.md, line 28

    curl -fsSL https://raw.githubusercontent.com/majiayu000/spellbook/main/install.sh | bash -s -- --target all

    docs/migration-from-claude-arsenal.md, line 31

    curl -fsSL https://raw.githubusercontent.com/majiayu000/spellbook/main/install.sh | bash -s -- --target claude

    docs/migration-from-claude-arsenal.md, line 34

    curl -fsSL https://raw.githubusercontent.com/majiayu000/spellbook/main/install.sh | bash -s -- --target codex

    skills/python-project/SKILL.md, line 90

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

    skills/python-project/reference/tech-stack.md, line 29

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

  • Network

    Serious

    accepts a host from input, with no fixed list in this file.

    NETWORK_HOST_FROM_INPUT

    plugins/idea-coach/skills/idea-to-product/scripts/verify_prototype.py, line 161

    "fetch() is forbidden": r"\bfetch\b",

    skills/auth-security/SKILL.md, line 61

    const tokenResponse = await fetch('https://auth.example.com/token', {

    skills/auth-security/SKILL.md, line 362

    fetch('https://api.example.com/resource', {

    Show more

    skills/auth-security/reference/jwt.md, line 341

    const keys = await fetch(jku).then(r => r.json());

    skills/auth-security/reference/oauth2.1.md, line 38

    const response = await fetch('https://auth.example.com/token', {

    skills/auth-security/reference/oauth2.1.md, line 56

    const response = await fetch('https://auth.example.com/token', {

    skills/auth-security/reference/oauth2.1.md, line 143

    const response = await fetch(config.tokenEndpoint, {

    skills/clash-doctor/references/full-guide.md, line 357

    curl --noproxy '*' --connect-timeout 5 -s -o /dev/null -w "直连: HTTP=%{http_code} 耗时=%{time_total}s IP=%{remote_ip}\n" https://$TARGET 2>&1 || echo "直连: 失败(超时或拒绝)"

    skills/clash-doctor/references/full-guide.md, line 363

    curl -x http://127.0.0.1:PORT --connect-timeout 5 -s -o /dev/null -w "代理(PORT): HTTP=%{http_code} 耗时=%{time_total}s\n" https://$TARGET 2>&1 || echo "代理(PORT): 失败"

    skills/clash-doctor/references/full-guide.md, line 364

    curl -x socks5://127.0.0.1:PORT --connect-timeout 5 -s -o /dev/null -w "SOCKS5(PORT): HTTP=%{http_code} 耗时=%{time_total}s\n" https://$TARGET 2>&1 || echo "SOCKS5(PORT): 失败"

    skills/cliproxy-newapi-stack/scripts/deploy_newapi.sh, line 57

    if curl -fsS -o /dev/null "http://127.0.0.1:${port}/api/setup"; then

    skills/devops-excellence/reference/release-strategies.md, line 253

    curl http://localhost:8080/health

    skills/gemma4-local-deploy/references/llama-cpp.md, line 129

    curl -fsS http://127.0.0.1:8080/v1/models | jq '.data[0].meta | {n_ctx, n_ctx_train, n_params, size}'

    skills/gemma4-local-deploy/references/ollama.md, line 12

    curl -fsS http://127.0.0.1:11434/api/version

    skills/gemma4-local-deploy/references/verification.md, line 8

    curl -fsS http://127.0.0.1:8080/health

    skills/gemma4-local-deploy/references/verification.md, line 9

    curl -fsS http://127.0.0.1:8080/v1/models

    skills/gemma4-local-deploy/references/verification.md, line 10

    curl -fsS http://127.0.0.1:8080/v1/chat/completions \

    skills/idea-to-product/scripts/verify_prototype.py, line 161

    "fetch() is forbidden": r"\bfetch\b",

  • Secrets

    Concern

    reads a credential or environment file.

    SECRETS_ENV_READ SECRETS_PATH_CREDENTIAL SECRETS_PATH_DOTENV

    agents/security-auditor.md, line 355

    find . -name "*.env*" -o -name "*.config.*" -o -name "*.yaml"

    agents/security-auditor.md, line 365

    grep -rE "(api_key|apikey|secret|password|token|credential)" --include="*.ts" --include="*.env*"

    skills/cliproxy-newapi-stack/SKILL.md, line 67

    SSH_TARGET=root@<HOST> SSH_KEY=~/.ssh/id_ed25519 PORT=8200 \

    Show more

    agents/security-auditor.md, line 394

    cat .env.example # Check for sensitive defaults

    skills/cliproxy-newapi-stack/SKILL.md, line 115

    SSH_TARGET=root@<HOST> SSH_KEY=~/.ssh/id_ed25519 \

    skills/cliproxy-newapi-stack/SKILL.md, line 131

    SSH_TARGET=root@<HOST> SSH_KEY=~/.ssh/id_ed25519 \

    skills/cliproxy-newapi-stack/SKILL.md, line 172

    SSH_TARGET=root@<HOST> SSH_KEY=~/.ssh/id_ed25519 \

    skills/cliproxy-newapi-stack/SKILL.md, line 191

    SSH_TARGET=root@<HOST> SSH_KEY=~/.ssh/id_ed25519 \

    skills/cliproxy-newapi-stack/scripts/set_pricing.py, line 99

    key = os.environ.get("SSH_KEY", os.path.expanduser("~/.ssh/id_ed25519"))

    skills/devops-excellence/reference/release-strategies.md, line 755

    const ldClient = LDClient.init(process.env.LD_SDK_KEY);

    skills/ip-check/scripts/ipcheck.py, line 342

    key = os.environ.get("ABUSEIPDB_KEY")

    skills/ip-check/scripts/ipcheck.py, line 356

    qkey = os.environ.get("IPQS_KEY")

  • 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/product-manager-toolkit/references/prd_templates.md, line 1

    # PRD Templates

  • 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 ed52af74bce8. 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. accepts a host from input, with no fixed list in this file. 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: ed52af74bce85ba9e71db109c72708833012eaf2

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