Grades are a hygiene check, not a security guarantee.

Claude Code, Skill

Agent Skills

Agent Skills, a skill listed in the PlugVet directory.

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 6a74cf03a8a8, unchanged since the check below.

INSTALL_REMOTE_SCRIPT SECRETS_PATH_CREDENTIAL

Why this grade

  • INSTALL_REMOTE_SCRIPT High

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

    skills/devops/linkerd/SKILL.md, line 21 curl -fsL https://run.linkerd.io/install | sh

  • SECRETS_PATH_CREDENTIAL Medium

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

    skills/devops/ansible/SKILL.md, line 100 ansible_ssh_private_key_file=~/.ssh/prod_deploy.pem

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

    Pass

    No shell or command execution found, and no extra permission was declared.

  • Install and update

    Serious

    install fetches a script from the network.

    INSTALL_REMOTE_SCRIPT

    skills/devops/linkerd/SKILL.md, line 21

    curl -fsL https://run.linkerd.io/install | sh

    skills/tools/iterm2/SKILL.md, line 21

    curl -L https://iterm2.com/shell_integration/install_shell_integration.sh | bash

  • Network

    Concern

    can reach a host that is not written as a fixed address. can reach admin. The description does not name that host. can reach awscli.amazonaws.com. The description does not name that host. can reach s3.amazonaws.com. The description does not name that host. can reach api.render.com. The description does not name that host. can reach api.myjson.com. The description does not name that host. can reach jsonplaceholder.typicode.com. The description does not name that host. can reach keycloak. The desc

    NETWORK_NO_FIXED_HOST NETWORK_UNNAMED_HOST NETWORK_NAMED_HOST

    skills/ai-ml/comfyui/SKILL.md, line 46

    with urllib.request.urlopen(req) as response:

    skills/ai-ml/comfyui/SKILL.md, line 141

    with urllib.request.urlopen(req) as response:

    skills/ai-ml/perplexity/SKILL.md, line 94

    res = requests.post(url, json=payload, headers=headers)

    Show more

    skills/architecture/websockets/SKILL.md, line 38

    const socket = new WebSocket("ws://localhost:8080");

    skills/databases/couchdb/SKILL.md, line 21

    curl -X PUT http://admin:[email protected]:5984/my_database/doc1 \

    skills/databases/couchdb/SKILL.md, line 33

    curl -X POST http://admin:[email protected]:5984/mydb \

    skills/databases/couchdb/SKILL.md, line 39

    curl -X GET http://admin:[email protected]:5984/mydb/8f3d1e1c...

    skills/databases/couchdb/SKILL.md, line 48

    curl -X PUT http://admin:[email protected]:5984/mydb/8f3d1e1c... \

    skills/databases/couchdb/SKILL.md, line 78

    REV=$(curl -s "http://127.0.0.1:5984/mydb/doc1" | jq -r '._rev')

    skills/databases/couchdb/SKILL.md, line 81

    curl -X PUT "http://127.0.0.1:5984/mydb/doc1" -H "Content-Type: application/json" -d "{"_rev": "$REV", "title": "Updated Document", "status": "resolved"}"

    skills/databases/influxdb/SKILL.md, line 74

    curl -XPOST "http://localhost:8086/api/v2/wri

    skills/devops/caddy/SKILL.md, line 97

    curl http://localhost:2019/config/ | jq .

    skills/devops/consul/SKILL.md, line 88

    curl -s http://127.0.0.1:8500/v1/health/service/payment-api?passing=true | jq .

    skills/devops/docker/SKILL.md, line 67

    CMD wget --no-verbose --tries=1 --spider http://localhost:3000/healthz || exit 1

    skills/testing/webdriver/SKILL.md, line 56

    curl -X POST http://localhost:9515/session \

    skills/testing/webdriver/SKILL.md, line 62

    curl -X POST http://localhost:9515/session/8f3d1e1c/url \

  • Secrets

    Concern

    reads a credential or environment file.

    SECRETS_ENV_READ SECRETS_PATH_CREDENTIAL SECRETS_PATH_DOTENV

    skills/ai-ml/claude/SKILL.md, line 46

    client = Anthropic(api_key=os.environ.get("ANTHROPIC_API_KEY"))

    skills/ai-ml/dalle/SKILL.md, line 45

    client = OpenAI(api_key=os.environ.get("OPENAI_API_KEY"))

    skills/devops/ansible/SKILL.md, line 100

    ansible_ssh_private_key_file=~/.ssh/prod_deploy.pem

    Show more

    skills/ai-ml/deepseek/SKILL.md, line 51

    api_key=os.environ.get("DEEPSEEK_API_KEY"),

    skills/ai-ml/gemini/SKILL.md, line 44

    client = genai.Client(api_key=os.environ.get("GEMINI_API_KEY"))

    skills/ai-ml/mistral/SKILL.md, line 42

    client = Mistral(api_key=os.environ.get("MISTRAL_API_KEY"))

    skills/ai-ml/openai-gpt/SKILL.md, line 54

    client = OpenAI(api_key=os.environ.get("OPENAI_API_KEY"))

    skills/ai-ml/perplexity/SKILL.md, line 49

    api_key=os.environ.get("PERPLEXITY_API_KEY"),

    skills/ai-ml/perplexity/SKILL.md, line 81

    "Authorization": f"Bearer {os.environ.get('PERPLEXITY_API_KEY')}",

    skills/devops/vercel/SKILL.md, line 98

    # Pull production environment variables to local .env

    skills/devops/vercel/SKILL.md, line 99

    vercel env pull .env.local

    skills/tools/datagrip/SKILL.md, line 72

    Auth: Public Key (~/.ssh/id_ed25519)

    skills/tools/dbeaver/SKILL.md, line 45

    Private Key: ~/.ssh/bastion_key.pem

    skills/tools/tableplus/SKILL.md, line 56

    - Private Key: ~/.ssh/bastion-id_ed25519

    skills/ai-ml/cursor-ai/SKILL.md, line 116

    - Configure `.cursorignore` to prevent indexing of generated files, `.env` secrets, and build output directories.

    skills/devops/awscli/SKILL.md, line 119

    - Commit `~/.aws/credentials` or access keys to Git repositories.

  • 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 6a74cf03a8a8. install fetches a script from the network. can reach a host that is not written as a fixed address. can reach admin. The description does not name that host. can reach awscli.amazonaws.com. The description does not name that host. can reach s3.amazonaws.com. The description does not name that host. can reach api.render.com. The description does not name that host. can reach api.myjson.com. The description does not name that host. can reach jsonplaceholder.typicode.com. The description does not name that host. can reach keycloak. The desc reads a credential or environment file.

Date and source

Date checked:

View source

github.com

Commit graded: 6a74cf03a8a86dc7d993ead3091b41123dbd0181

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