Claude Code, Plugin
Market Intel
Thin Claude Code skill for commercial/market research.
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 1046cd8740e7.
INSTALL_UNPINNED NETWORK_UNNAMED_HOST SECRETS_PATH_UNCONFIRMED PERMISSION_SHELL_DECLARED NETWORK_NAMED_HOST SECRETS_ENV_READ
Why this grade
- INSTALL_UNPINNED Low
Dependencies use a range or git URL with no lockfile.
requirements.txt, line 3
requests - NETWORK_UNNAMED_HOST Low
Calls a fixed host that the description does not name.
skills/market-intel/reference/tools/defillama.md, line 15
curl https://api.llama.fi/protocols - SECRETS_PATH_UNCONFIRMED Low
The Secrets check reports a credential or environment file, but no quoted line shows a recognisable path.
tools/discover.py, line 214
if os.environ.get("GITHUB_TOKEN"): - PERMISSION_SHELL_DECLARED Note
Runs shell commands, and the manifest or description says so.
tools/changelog_draft.py, line 139
proc = subprocess.run( - NETWORK_NAMED_HOST Note
Calls a fixed host that the description names.
skills/market-intel/reference/tools/defillama.md, line 15
curl https://api.llama.fi/protocols - SECRETS_ENV_READ Note
Reads an environment variable whose name contains KEY, SECRET, TOKEN, PASSWORD or CREDENTIAL.
tools/discover.py, line 214
if os.environ.get("GITHUB_TOKEN"):
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
tools/changelog_draft.py, line 139
proc = subprocess.run(
tools/check_all.py, line 56
kit = subprocess.run(["git", "config", "--get", key], cwd=REPO, capture_output=True,
tools/check_all.py, line 88
p = subprocess.run(command + [path] + argv, cwd=REPO,
Show more
tools/deploy_skill.sh, line 126
return subprocess.run(["git", *args], cwd=repo, check=True, stdout=subprocess.PIPE).stdout
tools/deploy_skill.sh, line 149
subprocess.run([sys.executable, "tools/verify_matrix.py", "--no-net", "--no-cache"], cwd=repo, check=True)
tools/emit_metrics.py, line 51
return subprocess.run(["git", "rev-parse", "--short", "HEAD"], cwd=ROOT,
tools/git_baseline.py, line 30
result = subprocess.run(["git", "-c", "core.fsmonitor=false", "--literal-pathspecs", *args],
tools/human_review.py, line 71
result = subprocess.run(["git", *arguments], check=True, capture_output=True,
Install and update
Concern
dependencies are not pinned.
INSTALL_UNPINNED
requirements.txt, line 3
requests
Network
Concern
can reach api.llama.fi. The description does not name that host. can reach api.fxtwitter.com.
NETWORK_UNNAMED_HOST NETWORK_NAMED_HOST
skills/market-intel/reference/tools/defillama.md, line 15
curl https://api.llama.fi/protocols
skills/market-intel/reference/tools/defillama.md, line 25
curl https://api.llama.fi/tvl/aave # -> single number, current USD TVL
skills/market-intel/reference/tools/fxembed.md, line 21
curl -s "https://api.fxtwitter.com/i/status/<TWEET_ID>" | jq '.tweet | {text, author: .author.screen_name, media: .media}'
Show more
skills/market-intel/reference/tools/fxembed.md, line 23
curl -s "https://api.fxembed.com/<handle>/post/<rkey>"
skills/market-intel/reference/tools/google-suggest.md, line 25
curl "https://suggestqueries.google.com/complete/search?client=firefox&q=patio-heater+led+light+bar&hl=en&gl=us"
skills/market-intel/reference/tools/google-suggest.md, line 31
r = requests.get("https://suggestqueries.google.com/complete/search",
skills/market-intel/reference/tools/idea-reality-mcp.md, line 31
curl -X POST https://idea-reality-mcp.onrender.com/api/check \
skills/market-intel/reference/tools/scrapling.md, line 21
page = StealthyFetcher.fetch("https://target-behind-cloudflare.example", headless=True)
Secrets
Concern
reads a credential or environment file.
SECRETS_ENV_READ SECRETS_PATH_UNCONFIRMED
tools/discover.py, line 214
if os.environ.get("GITHUB_TOKEN"):
scripts/init_config.py, line 20
*.env
scripts/init_config.py, line 21
!*.env.template
Show more
scripts/init_config.py, line 37
`*.env` files back into this directory, then re-running the skill's verify script.
scripts/init_config.py, line 40
Per tool, create `secrets/<slug>.env` with the KEY=VALUE pairs its `tools/<slug>/env.template` lists.
scripts/init_config.py, line 180
print(" secrets/<slug>.env with real values (gitignored).")
scripts/verify_config.py, line 180
check("Mode B .gitignore blocks secrets (secrets/* + *.env)",
scripts/verify_config.py, line 181
"secrets/" in txt and "*.env" in txt)
skills/market-intel/reference/companion-config-spec.md, line 72
└── <slug>.env # OPTIONAL (only when tool has env vars)
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 1046cd8740e7. requests shell access. The manifest names this permission. dependencies are not pinned. can reach api.llama.fi. The description does not name that host. can reach api.fxtwitter.com. reads a credential or environment file.
Date and source
Date checked:
github.com
Commit graded: 1046cd8740e784d379459a0b5c9e6a003f6cce8e
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.