Grades are a hygiene check, not a security guarantee.

Claude Code, Skill

Claude Skills

Open, ready-to-install Claude Skills for B2B go-to-market teams — HubSpot, Salesforce, LinkedIn, paid ads, and outbound — built by Growth Today, an AI-native GTM engineering firm.

Compatibility: Not stated.

Grade D

Two or more Medium findings, or a High. Only try it in a sandbox.

Graded by PlugVetRubric v2

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

AGENT_HIDDEN_STEP

Why this grade

  • AGENT_HIDDEN_STEP High

    Text tells the agent to hide a step or not to tell the user.

    clay-search-query/SKILL.md, line 76 filter in the query; this is captured - do NOT tell the user it was uncaptured. |

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

    Pass

    No shell or command execution found, and no extra permission was declared.

  • 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.hubapi.com. The description does not name that host.

    NETWORK_NO_FIXED_HOST NETWORK_UNNAMED_HOST

    gt-hubspot-admin/playbooks/assign-unowned-contacts/scripts/after.py, line 46

    resp = requests.post(SEARCH_URL, headers=HEADERS, json={

    gt-hubspot-admin/playbooks/assign-unowned-contacts/scripts/before.py, line 41

    resp = requests.post(SEARCH_URL, headers=HEADERS, json={

    gt-hubspot-admin/playbooks/assign-unowned-contacts/scripts/before.py, line 58

    resp_all = requests.get(

    Show more

    gt-hubspot-admin/playbooks/assign-unowned-contacts/scripts/before.py, line 93

    owners_resp = requests.get(f"{BASE}/crm/v3/owners", headers=HEADERS)

    gt-hubspot-admin/playbooks/assign-unowned-contacts/scripts/execute.py, line 65

    resp = requests.post(SEARCH_URL, headers=HEADERS, json=body)

    gt-hubspot-admin/playbooks/assign-unowned-contacts/scripts/execute.py, line 103

    resp = requests.post(update_url, headers=HEADERS, json=payload)

    gt-hubspot-admin/playbooks/assign-unowned-contacts/scripts/execute.py, line 138

    owner_resp = requests.get(f"{BASE}/crm/v3/owners/{TARGET_OWNER_ID}", headers=HEADERS)

    gt-hubspot-admin/playbooks/build-smart-lists/scripts/execute.py, line 339

    resp = requests.post(create_url, headers=HEADERS, json=list_def)

  • Secrets

    Concern

    reads a credential or environment file.

    SECRETS_PATH_DOTENV

    gt-hubspot-admin/playbooks/assign-unowned-contacts/scripts/after.py, line 22

    load_dotenv(os.path.join(os.path.dirname(__file__), "..", ".env"))

    gt-hubspot-admin/playbooks/assign-unowned-contacts/scripts/before.py, line 26

    load_dotenv(os.path.join(os.path.dirname(__file__), "..", ".env"))

    gt-hubspot-admin/playbooks/assign-unowned-contacts/scripts/execute.py, line 13

    Set TARGET_OWNER_ID below (or in .env as HUBSPOT_TARGET_OWNER_ID).

    Show more

    gt-hubspot-admin/playbooks/assign-unowned-contacts/scripts/execute.py, line 28

    load_dotenv(os.path.join(os.path.dirname(__file__), "..", ".env"))

    gt-hubspot-admin/playbooks/assign-unowned-contacts/scripts/execute.py, line 132

    print(" Set it in this script or as HUBSPOT_TARGET_OWNER_ID in .env")

    gt-hubspot-admin/playbooks/build-smart-lists/scripts/execute.py, line 39

    load_dotenv(os.path.join(os.path.dirname(__file__), "..", ".env"))

    gt-hubspot-admin/playbooks/create-icp-tiers/scripts/after.py, line 28

    load_dotenv(os.path.join(os.path.dirname(__file__), "..", ".env"))

    gt-hubspot-admin/playbooks/create-icp-tiers/scripts/before.py, line 33

    load_dotenv(os.path.join(os.path.dirname(__file__), "..", ".env"))

  • Agent instructions

    Serious

    instructions tell the agent to hide a step.

    AGENT_HIDDEN_STEP

    clay-search-query/SKILL.md, line 76

    filter in the query; this is captured - do NOT tell the user it was uncaptured. |

    clay-search-query/SKILL.md, line 228

    first pass. That mapping is captured - do NOT tell the user the subindustry labels were uncaptured,

    clay-search-query/SKILL.md, line 540

    already satisfied, so it is captured - do NOT tell the user it was uncaptured.

    Show more

    clay-search-query/SKILL.md, line 603

    boundary widens to the nearest bucket; do not tell the user it was uncaptured.

  • 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

    gt-linkedin-content/resources/posts/brigi-posts-reference.csv, line 1

    # Brigi (Growth Today) posts - reference set for the Growth Today LinkedIn Content skill.

    gt-linkedin-content/resources/posts/jani-posts-reference.csv, line 1

    # Jani (Growth Today) posts - reference set for the Growth Today LinkedIn Content skill.

    gt-salesforce-admin/playbooks/review-bounced-records/playbook.md, line 1

    ---

  • 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 9eacad3ed2b9. can reach a host that is not written as a fixed address. can reach api.hubapi.com. The description does not name that host. reads a credential or environment file. instructions tell the agent to hide a step. 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:

View source

github.com

Commit graded: 9eacad3ed2b933f3bb105229ec626db85cc7d9a0

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