jbvc/django-verification
Verification loop for Django projects: migrations, linting, tests with coverage, security scans, and deployment readiness checks before release or PR.
55
69%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
High
Do not use without reviewing
Security
1 high severity finding. You should review these findings carefully before considering using this skill.
W007: Insecure credential handling detected in skill instructions.
What this means
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
Why it was flagged
The prompt includes plaintext credentials and example secrets directly in commands and CI env (e.g., DJANGO_SECRET_KEY: test-secret-key, DATABASE_URL with password, and a superuser created with password 'admin'), which forces the agent to emit secret values verbatim if it reproduces those steps or templates.
Where we found it
[REDACTED]
secret · 3 sites
The CI workflow example embeds a DATABASE_URL with plaintext password 'postgres' in the env block, which the agent would emit verbatim when reproducing this template.
SKILL.md
444
DATABASE_URL: [REDACTED]
SKILL.md
445
DJANGO_SECRET_KEY: [REDACTED]
SKILL.md
153
echo "from apps.users.models import User; User.objects.create_superuser('[REDACTED]@example.com', '[REDACTED]')" | python manage.py shell
- Audited
- Security analysis