oss-ds-supply-chain-auditor

name

oss-ds-supply-chain-auditor

description

Audit open-source packages, notebooks, model weights, datasets, licenses, and provenance used in data science work. Use when an agent needs a judgment-heavy data science workflow for audit ds dependencies, models, data, and licenses, including evidence review, local artifact inspection, risk classification, stakeholder-ready decisions, reproducibility, governance, or agent-to-agent handoff. Trigger for Codex, Claude, Gemini, Copilot, Cursor, Windsurf, Gravity, LangGraph, CrewAI, AutoGen, or local agents when this exact workflow is needed.

OSS Data Science Supply Chain Auditor

Mission

Audit open-source packages, notebooks, model weights, datasets, licenses, and provenance used in data science work.

Current pain point: Data science supply chains include packages, model files, datasets, and notebooks that standard app audits often miss.

Why this skill exists: A DS-specific audit catches model/data provenance and notebook execution risks alongside dependency risk.

Operating Rules

• Start by restating the decision this skill is supporting.
• Inspect local artifacts first before asking for context.
• Treat scripts as evidence collectors, not as substitutes for judgment.
• Preserve raw data, notebooks, configs, and model artifacts unless the user explicitly asks for mutation.
• Mark missing context as unknown, not provided, or owner decision; do not invent it.
• Classify each blocker as stop, fix-first, monitor, accepted risk, or owner decision.
• Use the output contract exactly unless the user asks for a different format.
• Keep final recommendations auditable: every important claim needs evidence, assumption, or caveat.

What This Skill Must Do

• Transform a vague request into an explicit OSS Data Science Supply Chain Auditor decision with named owner, evidence, assumptions, and action threshold.
• Inspect local artifacts first: data extracts, schemas, notebooks, SQL, pipeline configs, model reports, tickets, and prior decisions.
• Separate mechanical checks from expert judgment so another reviewer can reproduce what was checked and what was inferred.
• Classify findings as stop, fix-first, monitor, accepted risk, or owner decision instead of producing generic advice.
• Preserve raw evidence and never silently mutate data, notebooks, model artifacts, or production configs.
• Return a decision artifact that can be handed to a data scientist, ML engineer, governance reviewer, or stakeholder without hidden context.

Required Inputs

• repo path
• environment files
• notebooks
• model artifact paths
• dataset sources
• license expectations

If an input is missing, inspect available files first. Ask only for information that cannot be recovered from the workspace and would change the recommendation.

Workflow

1. Inventory Python, R, system, notebook, model, and dataset dependencies.
2. Flag unknown sources, unsafe install patterns, large binary artifacts, and license uncertainty.
3. Review notebooks for shell execution, remote downloads, credential exposure, and hidden outputs.
4. Create a DS SBOM-style summary with risk levels and remediation priorities.
5. Return a supply-chain risk report and minimum cleanup plan.

Red Flags

• pip install from unpinned URL
• unknown model weights
• dataset license absent
• notebook output leaks secrets
• native binary dependency unreviewed

When a red flag appears, slow down and surface it in Risks. A red flag does not always mean stop, but it must change the recommendation or the confidence level.

Resources

• Read references/playbook.md for the skill-specific checklist, scoring rubric, and failure modes.
• Read references/acceptance-tests.md before forward-testing clean, messy, and adversarial requests.
• Read references/agent-portability.md when adapting this skill to Claude, Gemini, Copilot, Cursor, Windsurf, Gravity, LangGraph, CrewAI, AutoGen, or local agents.
• Read references/quality-rubric.md when reviewing whether the output meets senior data-science standards.
• Use scripts/quick_validate_skill.py . --strict before publishing or installing the skill.

Use only the specific reference file needed for the task; keep context small.

Output Contract

Return these sections unless the user requests another format:

• Problem: the decision, artifact, model, data source, or workflow being handled.
• Inputs: files, data, stakeholder context, assumptions, and missing context used.
• Checks performed: concrete inspections, scripts, and reasoning checks.
• Findings: prioritized observations with evidence.
• Decision: go, fix-first, stop, proceed-with-risk, or needs-owner-review.
• Risks: unresolved blockers, caveats, and owner decisions.
• Next actions: smallest useful follow-up steps.
• Artifacts: generated files, specs, reports, scripts, or links.

Final Checks

• Did the response answer the actual decision, not just analyze data?
• Did it preserve evidence and avoid silent mutation?
• Did it name unknowns and owner decisions?
• Did it include at least one concrete next action?
• Did it avoid overclaiming causality, readiness, compliance, or production safety?