Grades are a hygiene check, not a security guarantee.

Claude Code, Skill

Agent Skills

Any skill, from any repo, wired into every harness — just ask.

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.

INSTALL_REMOTE_SCRIPT

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.py, line 117 subprocess.run(["bash", "-c", "curl -fsSL https://opencode.ai/install | bash"], check=False)

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

    install.py, line 113

    subprocess.run(cmd, check=False)

    install.py, line 117

    subprocess.run(["bash", "-c", "curl -fsSL https://opencode.ai/install | bash"], check=False)

    install.py, line 120

    subprocess.run(["npm", "install", "-g", "opencode-ai"], check=False)

    Show more

    install.py, line 207

    subprocess.run(["cmd", "/c", "mklink", "/J", str(dest), str(src)],

    install.py, line 290

    subprocess.run(cmd, check=True)

    install.py, line 315

    subprocess.run([sys.executable, str(REPO_DIR / "scripts" / "gen-install-status.py"), "--open"],

  • Install and update

    Serious

    install fetches a script from the network.

    INSTALL_REMOTE_SCRIPT

    install.py, line 117

    subprocess.run(["bash", "-c", "curl -fsSL https://opencode.ai/install | bash"], check=False)

    install.py, line 183

    err("Install opencode: curl -fsSL https://opencode.ai/install | bash (Unix)")

    scripts/gen-install-status.py, line 63

    return "irm https://opencode.ai/install | iex" if os.name == "nt" else "curl -fsSL https://opencode.ai/install | bash"

    Show more

    docs/index.html, line 321

    via the official installer (<code>curl -fsSL https://opencode.ai/install | bash</code>

  • Network

    Concern

    can reach a host that is not written as a fixed address. can reach ollama.com. The description does not name that host.

    NETWORK_NO_FIXED_HOST NETWORK_UNNAMED_HOST

    docs/index.html, line 659

    fetch("install-status.json" + "?t=" + Date.now())

    rules/codex/default.rules, line 6

    prefix_rule(pattern=["node", "-e", "fetch('http://127.0.0.1:3100').then(async (r) => { console.log(r.status); console.log((await r.text()).slice(0,1200)); }).catch((err) => { conso

    rules/codex/default.rules, line 7

    prefix_rule(pattern=["node", "-e", "fetch('http://127.0.0.1:3100').then(async (r) => { console.log(r.status); console.log((await r.text()).slice(0,200)); }).catch((err) => { consol

    Show more

    rules/codex/default.rules, line 41

    prefix_rule(pattern=["node", "--input-type=module", "-e", "import 'dotenv/config'; const response = await fetch('https://ollama.com/api/web_search', { method: 'POST', headers: { Au

    scripts/status-template.html, line 261

    fetch("install-status.json" + "?t=" + Date.now())

  • Secrets

    Concern

    reads a credential or environment file.

    SECRETS_PATH_DOTENV

    scripts/merge.py, line 173

    m = re.match(r"^\[mcp_servers(?:\.([^.\]]+))?(?:\.env)?\]\s*$", line.strip())

    scripts/merge.py, line 175

    cur_name, cur_env = m.group(1), ".env" in line

    scripts/merge.py, line 375

    out.append(f"\n[mcp_servers.{name}.env]\n")

    Show more

    .gitignore, line 14

    *.env

    skills/enhance-repo/SKILL.md, line 47

    - Check `.gitignore` and `.dockerignore` cover env files (`.env`, `.env.*`, `*.pem`, `*.key`, credential stores). Warn if committed env files exist; ask before rewriting history.

    skills/enhance-repo/SKILL.md, line 83

    - Add API documentation for public endpoints (OpenAPI/Swagger or docstrings); document env vars in `.env.example` with comments.

    skills/enhance-repo/SKILL.md, line 91

    - Report a concise summary organized by area: what was added, what was changed, what was intentionally skipped, and follow-ups (e.g. "run `npm test` before pushing", "rotate the le

  • Agent instructions

    Pass

    No instruction to ignore earlier instructions or to hide a step.

  • Obfuscation

    Pass

    No encoded or minified payload found.

  • Licence

    Note

    no licence file found.

    LICENCE_MISSING

    No file path was stored.

    no licence file found.

  • Maintainer activity

    Pass

    The latest commit is within the last 365 days.

Note

Hygiene check of commit d16c92739859. requests shell access. The manifest names this permission. install fetches a script from the network. can reach a host that is not written as a fixed address. can reach ollama.com. The description does not name that host. reads a credential or environment file. no licence file found.

Date and source

Date checked:

View source

github.com

Commit graded: d16c9273985915b065ea5361e579f8e4414c4cdb

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