Grades are a hygiene check, not a security guarantee.

Claude Code, Skill

Fieldwork Skills

Teach your AI agent to operate 10x better.

Compatibility: Not stated.

Grade C

One Medium finding. Read the findings before installing.

Graded by PlugVetRubric v2

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

Rescanned at commit ff75bd17dd5a, unchanged since the check below.

SECRETS_PATH_CREDENTIAL

Why this grade

  • SECRETS_PATH_CREDENTIAL Medium

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

    skills/google-workspace-ops/references/auth-setup.md, line 73 gog auth credentials set /path/to/downloaded/credentials.json

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

    skills/browser-ops/scripts/mailbox.py, line 32

    result = subprocess.run(

    skills/trueskill-rank/scripts/trueskill-rank.py, line 918

    proc = subprocess.run(

    skills/video-gen/scripts/assemble.py, line 25

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

    Show more

    skills/video-gen/scripts/character_sheet.py, line 236

    proc = subprocess.run(cmd, capture_output=True, text=True)

    skills/video-gen/scripts/clip.py, line 163

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

    skills/video-gen/scripts/clip.py, line 383

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

    skills/video-gen/scripts/clip.py, line 431

    update_proc = subprocess.run(update_cmd, capture_output=True, text=True, check=False)

    skills/video-gen/scripts/generate.py, line 249

    result = subprocess.run([vault_bin, "get", "FAL_KEY"],

  • Install and update

    Note

    The docs document an installer that pipes a download into a shell.

    INSTALL_DOCUMENTED_INSTALLER

    skills/gsd-coordinator/references/installation-guide.md, line 57

    If `bun: command not found`: install Bun first: `curl -fsSL https://bun.sh/install | bash`

    skills/gsd-coordinator/references/installation-guide.md, line 95

    | `bun: command not found` | Install Bun: `curl -fsSL https://bun.sh/install \| bash` |

  • Network

    Concern

    can reach raw.githubusercontent.com. The description does not name that host. can reach openrouter.ai. The description does not name that host. can reach api.openai.com. The description does not name that host. 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 graph.instagram.com. The description does not name that host. can reach queue.fal.run. The description does not name that host. can reach fal.ai. The desc

    NETWORK_NO_FIXED_HOST NETWORK_UNNAMED_HOST NETWORK_NAMED_HOST

    skills/image-gen/SKILL.md, line 574

    curl -fsSL https://raw.githubusercontent.com/buildoak/fieldwork-skills/main/skills/image-gen/UPDATES.md | head -40

    skills/image-gen/references/api-reference.md, line 13

    curl -X POST https://openrouter.ai/api/v1/chat/completions \

    skills/image-gen/references/api-reference.md, line 35

    curl -X POST https://openrouter.ai/api/v1/chat/completions \

    Show more

    skills/image-gen/references/api-reference.md, line 55

    curl -X POST https://openrouter.ai/api/v1/chat/completions \

    skills/image-gen/references/api-reference.md, line 240

    curl -X POST https://api.openai.com/v1/images/edits \

    skills/image-gen/scripts/edit.py, line 92

    with urllib.request.urlopen(req, timeout=180) as resp:

    skills/image-gen/scripts/edit.py, line 239

    with urllib.request.urlopen(req, timeout=180) as resp:

    skills/image-gen/scripts/generate.py, line 532

    with urllib.request.urlopen(req, timeout=180) as resp:

    skills/peekaboo/playbooks/captcha-solver.md, line 98

    if ! curl -sf http://127.0.0.1:8080/v1/models >/dev/null 2>&1; then

    skills/peekaboo/playbooks/instagram-monitor.md, line 48

    if ! curl -sf http://127.0.0.1:8080/v1/models >/dev/null 2>&1; then

    skills/peekaboo/playbooks/safari-login.md, line 91

    if ! curl -sf http://127.0.0.1:8080/v1/models >/dev/null 2>&1; then

    skills/peekaboo/scripts/health-check.sh, line 61

    if curl -sf http://127.0.0.1:8080/v1/models >/dev/null 2>&1; then

  • Secrets

    Concern

    reads a credential or environment file.

    SECRETS_ENV_READ SECRETS_PATH_CREDENTIAL SECRETS_PATH_DOTENV

    skills/browser-ops/scripts/mailbox.py, line 22

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

    skills/google-workspace-ops/references/auth-setup.md, line 73

    gog auth credentials set /path/to/downloaded/credentials.json

    skills/google-workspace-ops/references/auth-setup.md, line 234

    gog auth credentials set /path/to/downloaded/credentials.json

    Show more

    skills/google-workspace-ops/references/installation-guide.md, line 79

    gog auth credentials set /path/to/downloaded/credentials.json

    skills/image-gen/scripts/edit.py, line 325

    api_key = os.environ.get("OPENROUTER_API_KEY_IMAGES") or os.environ.get("OPENROUTER_API_KEY")

    skills/image-gen/scripts/edit.py, line 338

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

    skills/image-gen/scripts/generate.py, line 416

    api_key = os.environ.get("OPENROUTER_API_KEY_IMAGES") or os.environ.get("OPENROUTER_API_KEY")

    skills/image-gen/scripts/review.py, line 174

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

    skills/trueskill-rank/scripts/trueskill-rank.py, line 944

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

    skills/trueskill-rank/scripts/trueskill-rank.py, line 1030

    if not os.environ.get("OPENAI_API_KEY"):

    skills/video-gen/scripts/generate.py, line 240

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

    .gitignore, line 21

    # Environment and secrets

    .gitignore, line 22

    .env

    .gitignore, line 24

    !.env.example

    .gitignore, line 25

    .envrc

    skills/browser-ops/UPDATE-GUIDE.md, line 32

    The AgentMail API key is stored in the user's environment (typically `~/.env.keys` or shell profile), not in the skill files. Updating the skill does not affect the API key. If the

  • 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.

Note

Hygiene check of commit ff75bd17dd5a. requests shell access. The manifest names this permission. The docs document an installer that pipes a download into a shell. can reach raw.githubusercontent.com. The description does not name that host. can reach openrouter.ai. The description does not name that host. can reach api.openai.com. The description does not name that host. 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 graph.instagram.com. The description does not name that host. can reach queue.fal.run. The description does not name that host. can reach fal.ai. The desc reads a credential or

Date and source

Date checked:

View source

github.com

Commit graded: ff75bd17dd5a89db9cf7a3e0b0efd167bd8dab66

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