Claude Code, Skill
Agent Toolkit
A curated collection of skills for AI coding agents.
Compatibility: Not stated.
Grade B
Minor issues only, no Medium or High. Worth a quick look at the findings below before installing.
Not a guarantee. A hygiene check of the source at the commit shown, not a security audit.
Rescanned at commit 3027f20f3181, unchanged since the check below.
PERMISSION_DELETE_FILES NETWORK_NO_FIXED_HOST NETWORK_UNNAMED_HOST SECRETS_PATH_DOTENV OBFUSCATION_ENCODED_BLOB SECRETS_ENV_READ
Why this grade
- PERMISSION_DELETE_FILES Low
Contains a call that can delete files.
scripts/build_plugins.py, line 135
shutil.rmtree(dist_dir) - NETWORK_NO_FIXED_HOST Low
Makes a network call whose host is not written as a fixed address.
skills/jira/references/mcp.md, line 303
curl -s -u "$JIRA_USER:$JIRA_API_TOKEN" \ - NETWORK_UNNAMED_HOST Low
Calls a fixed host that the description does not name.
skills/jira/references/mcp.md, line 303
curl -s -u "$JIRA_USER:$JIRA_API_TOKEN" \ - SECRETS_PATH_DOTENV Low
Mentions a .env file.
commands/codex-plan.md, line 102
- `.env.example` - Environment variables needed - OBFUSCATION_ENCODED_BLOB Low
Contains a long base64 shaped string in a file that should be readable.
agents/ui-ux-designer.md, line 238
d-image: url('data:image/svg+xml;base64,PHN2ZyB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciIHdpZHRoPSIzMDAiIGhlaWdodD0iMzAwIj48ZmlsdGVyIGlkPSJhIiB4PSIwIiB5PSIwIj48ZmVUdXJidWxlbmNl - SECRETS_ENV_READ Note
Reads an environment variable whose name contains KEY, SECRET, TOKEN, PASSWORD or CREDENTIAL.
skills/react-dev/examples/server-components.md, line 436
return process.env.SECRET_KEY; // Safe - never in client bundle
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
Concern
can delete files.
PERMISSION_DELETE_FILES
scripts/build_plugins.py, line 135
shutil.rmtree(dist_dir)
skills/session-handoff/evals/setup_test_env.py, line 29
subprocess.run(cmd, cwd=cwd, capture_output=True, check=True)
skills/session-handoff/evals/setup_test_env.py, line 41
shutil.rmtree(path)
Show more
skills/session-handoff/evals/setup_test_env.py, line 379
shutil.rmtree(path)
skills/session-handoff/scripts/check_staleness.py, line 28
result = subprocess.run(
skills/session-handoff/scripts/create_handoff.py, line 32
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.
NETWORK_NO_FIXED_HOST NETWORK_UNNAMED_HOST
skills/jira/references/mcp.md, line 303
curl -s -u "$JIRA_USER:$JIRA_API_TOKEN" \
skills/meme-factory/README.md, line 146
curl -I "https://api.memegen.link/images/buzz/test/test.png"
skills/meme-factory/SKILL.md, line 142
curl -I "https://api.memegen.link/images/buzz/test/test.png"
Show more
skills/react-dev/examples/server-components.md, line 38
const res = await fetch(`https://api.example.com/users/${id}`, {
skills/react-dev/references/hooks.md, line 263
fetch(url)
skills/react-dev/references/react-19-patterns.md, line 428
await fetch('/api/messages', {
skills/react-dev/references/react-19-patterns.md, line 480
const updated = await fetch(`/api/cart/${id}`, {
skills/react-dev/references/tanstack-router.md, line 135
const res = await fetch(`/api/users/${id}`);
skills/react-useeffect/alternatives.md, line 216
fetch(url)
Secrets
Concern
reads a credential or environment file.
SECRETS_ENV_READ SECRETS_PATH_DOTENV
commands/codex-plan.md, line 102
- `.env.example` - Environment variables needed
skills/react-dev/examples/server-components.md, line 436
return process.env.SECRET_KEY; // Safe - never in client bundle
skills/session-handoff/evals/setup_test_env.py, line 79
return jwt.sign({ id: user.id }, process.env.JWT_SECRET);
Agent instructions
Pass
No instruction to ignore earlier instructions or to hide a step.
Obfuscation
Concern
contains an encoded blob in a file that should be readable.
OBFUSCATION_ENCODED_BLOB
agents/ui-ux-designer.md, line 238
d-image: url('data:image/svg+xml;base64,PHN2ZyB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciIHdpZHRoPSIzMDAiIGhlaWdodD0iMzAwIj48ZmlsdGVyIGlkPSJhIiB4PSIwIiB5PSIwIj48ZmVUdXJidWxlbmNl
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 3027f20f3181. can delete files. can reach a host that is not written as a fixed address. can reach api.example.com. The description does not name that host. reads a credential or environment file. contains an encoded blob in a file that should be readable.
Date and source
Date checked:
github.com
Commit graded: 3027f20f3181758385a1bb8c022d4041dfb4de84
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.