Claude Code, Skill
Agentic Gtm
Fifteen GTM skills with playbooks, backed by a deterministic, approval-gated CLI.
Compatibility: Not stated.
Grade C
One Medium finding. Read the report before installing.
Not a guarantee. A hygiene check of the source at the commit shown, not a security audit.
PERMISSION_SHELL_UNDECLARED
Why this grade
- PERMISSION_SHELL_UNDECLARED Medium
Runs shell commands that the manifest or description does not mention.
scripts/generate_starter.py, line 28
shutil.rmtree(destination)
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. requests shell access. No manifest field names shell or command execution.
PERMISSION_SHELL_UNDECLARED PERMISSION_DELETE_FILES
scripts/generate_starter.py, line 28
shutil.rmtree(destination)
scripts/scan_public_release.py, line 96
history = 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.
NETWORK_NO_FIXED_HOST
src/agentic_gtm/adapters/slack/adapter.py, line 68
response = httpx.post(self.webhook, json=plan.payload, timeout=30)
Secrets
Concern
reads a credential or environment file.
SECRETS_ENV_READ SECRETS_PATH_DOTENV
scripts/generate_starter.py, line 66
cp .env.example .env
skills/handover-gtm-engine/references/handoff-template.md, line 120
| Credential name (from .env.example) | Holder today | Owner after | Channel | Rotate by | Rotation disconnects anything? |
skills/handover-gtm-engine/references/hard-rules-for-agents.md, line 14
7. Credentials live in .env only. Never in code, CLI arguments, logs, output, chat, or Git. Never print them. Never accept them as arguments.
Show more
src/agentic_gtm/config.py, line 59
raise RuntimeError(f"Missing {name}. Add it to .env; credentials are never CLI arguments.")
src/agentic_gtm/config.py, line 64
return bool(os.getenv("SUPABASE_URL") and os.getenv("SUPABASE_SERVICE_ROLE_KEY"))
src/agentic_gtm/workspace.py, line 54
- Secrets live only in `.env`. Contacts and provider IDs live only in the store, never in Git.
src/agentic_gtm/workspace.py, line 60
# Secret guard: blocks commits that ADD a secret value from .env or a
src/agentic_gtm/workspace.py, line 69
# 1) Any secret VALUE from .env appearing in added lines.
src/agentic_gtm/workspace.py, line 70
if [ -f "$repo_root/.env" ]; then
src/agentic_gtm/adapters/slack/adapter.py, line 20
self.token = token or os.getenv("SLACK_BOT_TOKEN", "").strip()
src/agentic_gtm/database/supabase.py, line 93
return bool(os.getenv("SUPABASE_URL") and os.getenv("SUPABASE_SERVICE_ROLE_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 2b411fe505a7. can delete files. requests shell access. No manifest field names shell or command execution. can reach a host that is not written as a fixed address. reads a credential or environment file.
Date and source
Date checked:
github.com
Commit graded: 2b411fe505a73d96fdfda00451b8fc9f381f6197
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.