ml-pipeline-automation
Automate ML workflows with Airflow, Kubeflow, MLflow. Use for reproducible pipelines, retraining schedules, MLOps, or encountering task failures, dependency errors, experiment tracking issues.
88
82%
Does it follow best practices?
Impact
100%
1.25xAverage score across 3 eval scenarios
Low
Low-risk findings worth noting
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
The skill's DAGs and Kubeflow pipelines explicitly load and validate data from external sources such as s3://my-bucket/data/train.csv and /data/*.csv and connect to external MLflow/Kubeflow endpoints (e.g., http://mlflow.example.com, http://kubeflow.example.com) whose untrusted/user-provided content is read and used to drive training, branching, and deployment decisions (see SKILL.md and references/* examples).
- Repository
- secondsky/claude-skills
- Commit
c4889f6
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.