Grades are a hygiene check, not a security guarantee.

Claude Code, Skill

Ai Skills

Ai Skills, a skill listed in the PlugVet directory.

Compatibility: Not stated.

Grade C

One Medium finding. Read the report before installing.

Graded by PlugVetRubric v2

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

SECRETS_PATH_CREDENTIAL

Why this grade

  • SECRETS_PATH_CREDENTIAL Medium

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

    .agents/skills/gh-cli/SKILL.md, line 656 gh repo deploy-key add ~/.ssh/id_rsa.pub \

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

    Note

    requests shell access. The manifest names this permission.

    PERMISSION_SHELL_DECLARED

    .agents/skills/docx/scripts/accept_changes.py, line 68

    result = subprocess.run(

    .agents/skills/docx/scripts/accept_changes.py, line 99

    subprocess.run(

    .agents/skills/docx/scripts/office/soffice.py, line 14

    subprocess.run(["soffice", ...], env=env)

    Show more

    .agents/skills/docx/scripts/office/soffice.py, line 37

    return subprocess.run(["soffice"] + args, env=env, **kwargs)

    .agents/skills/docx/scripts/office/soffice.py, line 59

    subprocess.run(

    .agents/skills/docx/scripts/office/validators/redlining.py, line 138

    result = subprocess.run(

    .agents/skills/docx/scripts/office/validators/redlining.py, line 167

    result = subprocess.run(

    .agents/skills/plugin-creator/scripts/package_plugin.py, line 39

    result = subprocess.run(

  • Install and update

    Pass

    No install-time script found, and dependencies are pinned or absent.

  • Network

    Concern

    can reach a host that is not written as a fixed address. can reach api.example.com. The description does not name that host. can reach assets4.lottiefiles.com. The description does not name that host. can reach kit.svel. The description does not name that host.

    NETWORK_NO_FIXED_HOST NETWORK_UNNAMED_HOST

    .agents/skills/extension-dev-skill/recipes/sys_http_request.md, line 131

    | 使用 `fetch()` 或 `XMLHttpRequest` | 沙箱环境限制 | 必须使用 `eda.sys_ClientUrl.request()` |

    .agents/skills/extension-dev-skill/recipes/sys_timer_websocket.md, line 153

    | 使用 `new WebSocket()` | 沙箱限制 | 使用 `eda.sys_WebSocket.register()` |

    .agents/skills/mcp-builder/reference/node_mcp_server.md, line 474

    const response = await axios.get(`${API_URL}/resource/${resourceId}`);

    Show more

    .agents/skills/mcp-builder/reference/node_mcp_server.md, line 480

    return axios.get(`${API_URL}/resource/${resourceId}`)

    .agents/skills/mcp-builder/reference/python_mcp_server.md, line 260

    response = requests.get(f"{API_URL}/resource/{resource_id}") # Blocks

    .agents/skills/microservices-architect/SKILL.md, line 72

    response = requests.get(f"{INVENTORY_URL}/stock/{order_id}", timeout=2)

    .agents/skills/playwright-cli/references/request-mocking.md, line 61

    const response = await route.fetch();

    .agents/skills/plugin-creator/references/best_practices.md, line 268

    const requests = this.requests.get(key) || [];

  • Secrets

    Concern

    reads a credential or environment file.

    SECRETS_PATH_CREDENTIAL SECRETS_PATH_DOTENV

    .agents/skills/gh-cli/SKILL.md, line 656

    gh repo deploy-key add ~/.ssh/id_rsa.pub \

    .agents/skills/gh-cli/SKILL.md, line 1730

    gh ssh-key add ~/.ssh/id_rsa.pub --title "My laptop"

    .agents/skills/gh-cli/SKILL.md, line 1733

    gh ssh-key add ~/.ssh/id_ed25519.pub --type "authentication"

    Show more

    .agents/skills/gh-cli/SKILL.md, line 1749

    gh gpg-key add ~/.ssh/id_rsa.pub

    .agents/skills/text-to-sql/SKILL.md, line 27

    - User creates `.env` file with connection details

    .agents/skills/text-to-sql/SKILL.md, line 70

    cp example.env .env

    .agents/skills/text-to-sql/SKILL.md, line 71

    # Edit .env with actual credentials

    .agents/skills/text-to-sql/SKILL.md, line 169

    ├── .env # MySQL credentials (if using MySQL)

  • 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

    .agents/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/sml.xsd, line 1

    <?xml version="1.0" encoding="utf-8"?>

    .agents/skills/extension-dev-skill/resources/references/interfaces/ILIB_ClassificationIndex.md, line 1

    # ILIB\_ClassificationIndex interface

  • 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 d9dfcd68f150. requests shell access. The manifest names this permission. can reach a host that is not written as a fixed address. can reach api.example.com. The description does not name that host. can reach assets4.lottiefiles.com. The description does not name that host. can reach kit.svel. The description does not name that host. 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: d9dfcd68f1503f05a2b70f6bac9e2db47f52b013

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