Claude Code, Plugin
Loamwright Seo Skill
Production-grade SEO + GEO content factory for Claude Code — research, write, fact-check, optimize, publish to WordPress, monitor.
Compatibility: Not stated.
Grade D
Two or more Medium findings, or a High finding. Only try it in a sandbox.
Not a guarantee. A hygiene check of the source at the commit shown, not a security audit.
Rescanned at commit cc3f19dac8fe, unchanged since the check below.
AGENT_IGNORE_INSTRUCTIONS NETWORK_HOST_FROM_INPUT
Why this grade
- AGENT_IGNORE_INSTRUCTIONS High
Text tells the agent to ignore earlier instructions.
agents/researcher.md, line 41
- `<!-- SYSTEM: ignore previous instructions -->` - NETWORK_HOST_FROM_INPUT Medium
A file takes a URL or endpoint as input and has no fixed host list.
scripts/_core/google_creds.py, line 65
resp = httpx.post(
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
hooks/stop_finalize.py, line 69
shutil.rmtree(d)
scripts/_core/prune_workspaces.py, line 157
shutil.rmtree(target)
scripts/_core/prune_workspaces.py, line 166
shutil.rmtree(RESEARCH_CACHE)
Show more
scripts/openai/image_fork.py, line 63
return subprocess.call(cmd)
scripts/pipeline/orchestrator.py, line 1700
shutil.rmtree(d)
scripts/pipeline/run_pipeline.py, line 134
return subprocess.run(command, shell=True, cwd=str(PLUGIN_ROOT),
scripts/pipeline/run_pipeline.py, line 146
subprocess.Popen(command, **kwargs)
scripts/release/opensource_export.py, line 165
proc = subprocess.run(
scripts/release/opensource_export.py, line 214
shutil.rmtree(child)
scripts/release/opensource_export.py, line 331
proc = subprocess.run(cmd, capture_output=True, text=True,
scripts/release/opensource_export.py, line 381
subprocess.run(["git", "init", "-b", "main"], cwd=out, check=True)
scripts/release/opensource_export.py, line 387
subprocess.run(cmd, cwd=out, check=True)
scripts/release/opensource_export.py, line 388
subprocess.run(["git", "add", "-A"], cwd=out, check=True)
Install and update
Concern
dependencies are not pinned.
INSTALL_UNPINNED
requirements.txt, line 2
httpx[http2]>=0.27.0,<1.0
Network
Serious
accepts a host from input, with no fixed list in this file.
NETWORK_HOST_FROM_INPUT
scripts/_core/google_creds.py, line 65
resp = httpx.post(
scripts/analysis/content_length_comparator.py, line 105
response = requests.get(url, headers=self.headers, timeout=10)
scripts/audit/business_type_detector.py, line 8
curl -s https://example.com | python -m scripts.audit.business_type_detector --url https://example.com
Show more
scripts/audit/ga4_fetch.py, line 28
def fetch(
scripts/audit/ga4_fetch.py, line 46
resp = httpx.post(
scripts/audit/ga4_fetch.py, line 82
data = fetch(args.property_id, days=args.days,
scripts/audit/google_oauth_setup.py, line 117
resp = httpx.post(TOKEN_ENDPOINT, data={
scripts/audit/google_oauth_setup.py, line 154
resp = httpx.post(TOKEN_ENDPOINT, data={
scripts/audit/gsc_fetch.py, line 30
def fetch(
scripts/fetch/tier_2_patchright.py, line 160
ap = argparse.ArgumentParser(description="Tier 2 patchright fetch (JS-heavy pages)")
scripts/lint/categories_sync_check.py, line 62
r = httpx.get(f"{url}/wp-json/wp/v2/categories", params={"per_page": 100}, auth=auth, timeout=30)
scripts/monitor/internal_link_graph.py, line 106
r = httpx.get(f"{creds.url}/wp-json/wp/v2/posts", headers=headers,
scripts/research/industry_news_runner.py, line 116
for toks, curl in fresh:
scripts/research/industry_news_runner.py, line 117
if curl and curl != eurl:
scripts/research/industry_news_runner.py, line 785
curl = canonical_url(head["url"])
scripts/research/industry_news_runner.py, line 786
if curl in by_url:
Secrets
Concern
reads a credential or environment file.
SECRETS_ENV_READ SECRETS_PATH_DOTENV
scripts/_core/credential_hub.py, line 579
key = os.environ.get("BING_INDEXNOW_KEY", "").strip()
scripts/_core/credential_hub.py, line 580
loc = os.environ.get("BING_INDEXNOW_KEY_LOCATION", "").strip()
scripts/_core/credential_hub.py, line 599
env_path = os.environ.get("GOOGLE_APPLICATION_CREDENTIALS", "").strip()
Show more
scripts/analysis/data_aggregator.py, line 30
load_dotenv('data_sources/config/.env')
scripts/analysis/dataforseo.py, line 26
self.password = password or os.getenv("DATAFORSEO_PASSWORD")
scripts/analysis/dataforseo.py, line 498
load_dotenv("data_sources/config/.env")
scripts/analysis/google_analytics.py, line 36
credentials_path = credentials_path or os.getenv("GA4_CREDENTIALS_PATH")
scripts/analysis/google_analytics.py, line 389
load_dotenv("data_sources/config/.env")
scripts/analysis/google_search_console.py, line 25
credentials_path = credentials_path or os.getenv('GSC_CREDENTIALS_PATH')
scripts/analysis/google_search_console.py, line 530
load_dotenv('data_sources/config/.env')
scripts/analysis/wordpress_publisher.py, line 46
self.app_password = app_password or os.getenv('WORDPRESS_APP_PASSWORD')
scripts/analysis/wordpress_publisher.py, line 459
env_path = Path(__file__).parent.parent.parent / '.env'
scripts/audit/google_oauth_setup.py, line 45
env_secret = os.environ.get("GOOGLE_OAUTH_CLIENT_SECRET", "")
scripts/release/opensource_export.py, line 68
.env
scripts/release/opensource_export.py, line 69
.env.local
.gitignore, line 22
*.pem
Agent instructions
Serious
instructions tell the agent to ignore earlier instructions.
AGENT_IGNORE_INSTRUCTIONS
agents/researcher.md, line 41
- `<!-- SYSTEM: ignore previous instructions -->`
scripts/validate/core_eeat_scorer.py, line 56
- <!-- ignore previous instructions -->
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
CHANGELOG.md, line 1
# Changelog
scripts/research/research_trending.py, line 1
#!/usr/bin/env python3
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 cc3f19dac8fe. can delete files. dependencies are not pinned. accepts a host from input, with no fixed list in this file. reads a credential or environment file. instructions tell the agent to ignore earlier instructions. 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:
github.com
Commit graded: cc3f19dac8fe0d323724d622a73b9cb16d0f6301
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.