Claude Code, Skill
Ai Skills
24 cross-platform agent skills for Claude Code, Cursor, Codex & Gemini CLI — databases, messaging, research, TTS, DevOps, and Google Workspace
Compatibility: Not stated.
Grade C
One Medium finding. Read the findings before installing.
Not a guarantee. A hygiene check of the source at the commit shown, not a security audit.
Rescanned at commit 281d88df1993, unchanged since the check below.
NETWORK_HOST_FROM_INPUT
Why this grade
- NETWORK_HOST_FROM_INPUT Medium
A file takes a URL or endpoint as input and has no fixed host list.
skills/apple-container/references/workflows.md, line 253
container run --rm -it web-test curl http://192.168.64.3
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/atlassian/scripts/confluence.py, line 714
handler = commands.get(args.command)
skills/atlassian/scripts/jira.py, line 807
handler = commands.get(args.command)
skills/elevenlabs/scripts/elevenlabs.py, line 239
result = subprocess.run(
Show more
skills/google-tts/scripts/google_tts.py, line 239
result = subprocess.run(
skills/notebooklm/scripts/auth_manager.py, line 148
shutil.rmtree(profile_dir, ignore_errors=True)
skills/notebooklm/scripts/remote_manager.py, line 1163
shutil.rmtree(temp_dir_path, ignore_errors=True)
skills/notebooklm/scripts/remote_manager.py, line 1390
shutil.rmtree(temp_dir, ignore_errors=True)
skills/outline/scripts/outline.py, line 645
handler = commands.get(args.command)
skills/whatsapp/scripts/wa.py, line 59
result = subprocess.run(["bash", bootstrap], stdout=subprocess.PIPE, text=True)
Install and update
Pass
No install-time script found, and dependencies are pinned or absent.
Network
Serious
accepts a host from input, with no fixed list in this file.
NETWORK_HOST_FROM_INPUT
skills/apple-container/references/workflows.md, line 253
container run --rm -it web-test curl http://192.168.64.3
skills/apple-container/references/workflows.md, line 280
curl http://my-web-server.test
skills/atlassian/scripts/auth.py, line 229
with urllib.request.urlopen(req, timeout=30) as resp:
Show more
skills/atlassian/scripts/auth.py, line 426
with urllib.request.urlopen(req, timeout=15) as resp:
skills/atlassian/scripts/mcp_client.py, line 80
with urllib.request.urlopen(req, timeout=60) as resp:
skills/azure-devops/scripts/api_client.py, line 105
with urllib.request.urlopen(req, timeout=30) as response:
skills/azure-devops/scripts/attachments.py, line 105
with urllib.request.urlopen(req, timeout=30) as response:
skills/azure-devops/scripts/auth.py, line 119
with urllib.request.urlopen(req, timeout=30) as resp:
skills/azure-devops/scripts/auth.py, line 228
with urllib.request.urlopen(req, timeout=15) as resp:
Secrets
Concern
reads a credential or environment file.
SECRETS_ENV_READ SECRETS_PATH_DOTENV
skills/atlassian/scripts/auth.py, line 70
"""Load environment variables from .env file if python-dotenv is available."""
skills/atlassian/scripts/auth.py, line 73
env_file = skill_dir / ".env"
skills/atlassian/scripts/auth.py, line 76
elif Path(".env").exists():
Show more
skills/atlassian/scripts/auth.py, line 129
api_token = os.environ.get("ATLASSIAN_API_TOKEN", "")
skills/atlassian/scripts/auth.py, line 562
print("Or use environment variables instead (see .env.example).", file=sys.stderr)
skills/deep-research/README.md, line 27
cp .env.example .env
skills/deep-research/README.md, line 28
# Edit .env and add your GEMINI_API_KEY
skills/deep-research/scripts/research.py, line 120
self.api_key = api_key or os.getenv("GEMINI_API_KEY")
skills/deep-research/scripts/research.py, line 123
"GEMINI_API_KEY not set. Set it in .env or environment variables."
skills/elevenlabs/scripts/elevenlabs.py, line 69
api_key = os.environ.get("ELEVENLABS_API_KEY")
skills/google-tts/scripts/google_tts.py, line 79
api_key = os.environ.get("GOOGLE_TTS_API_KEY")
skills/imagen/README.md, line 130
├── .env.example # API key template
skills/imagen/scripts/generate_image.py, line 42
api_key = os.environ.get("GEMINI_API_KEY")
skills/outline/scripts/outline.py, line 307
api_key = os.environ.get("OUTLINE_API_KEY", "")
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 281d88df1993. can delete files. accepts a host from input, with no fixed list in this file. reads a credential or environment file.
Date and source
Date checked:
github.com
Commit graded: 281d88df199357e3091a3be5c743a0fca9a9ae1b
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.