Skills wap-ingestion
📦

wap-ingestion

Content revision r1 Safe ⚙️ External commands🌐 Network access

Ingest S3 Data with WAP

Data teams need a safer way to load S3 files into Bauplan without changing main immediately. This skill guides a branch-based Write-Audit-Publish flow with checks before publish.

Supports: Claude Codex Code(CC)
🥉 78 Bronze

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request
Review the Skillstore skill "wap-ingestion" from https://skillstore.io/skills/bauplanlabs-wap-ingestion.md and its manifest at https://skillstore.io/api/skills/bauplanlabs-wap-ingestion/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Markdown detail GET /skills/bauplanlabs-wap-ingestion.md Signed manifest GET /api/skills/bauplanlabs-wap-ingestion/manifest Signed lockfile GET /api/skills/bauplanlabs-wap-ingestion/lockfile

Test it

Using "wap-ingestion". A user gives an S3 path, target table name, and inspect-on-success preference.

Expected outcome:

The assistant produces a WAP plan, a Python-based ingestion script outline, and a review checklist for the temporary branch.

Using "wap-ingestion". A user wants to append new files to an existing table.

Expected outcome:

The assistant explains how to skip table creation, import data on a branch, and validate the appended rows before merge.

Using "wap-ingestion". A reviewer asks how to publish an inspected branch.

Expected outcome:

The assistant describes the required main checkout, merge action, and optional branch cleanup with confirmation points.

Security Audit

Safe
v10 • 7/9/2026 Open versioned report

Most static findings are false positives caused by Markdown backticks around prose, SDK method names, and code fences. The skill does include legitimate local command usage for running the generated WAP script and for Bauplan CLI merge or cleanup steps, so those command-oriented findings are confirmed as medium risk. No prompt injection, credential exfiltration intent, or malicious network behavior was found.

2
Files scanned
263
Lines analyzed
4
Review items
0
False positives ignored
Capability review items (4)

These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.

Medium
SKILL.md:73-81
Ruby/shell backtick execution
```
The checklist explicitly tells the user to run a generated Python script with python wap_script.py. This is a legitimate workflow step, but it is still local command execution that should require user awareness.
Medium
SKILL.md:126-128
Ruby/shell backtick execution
When `on_success="inspect"` (default), the branch is left open for user review. If the user asks to
The prose directs the assistant to use the Bauplan CLI after inspection when the user asks to merge. These commands can publish data changes, so the external command risk is real even though it is contextual.
Medium
SKILL.md:128-137
Ruby/shell backtick execution
```bash
The bash block contains Bauplan CLI commands that checkout main, merge a branch, and optionally remove the branch. The commands are operationally legitimate but can change published data and delete review state.
Medium
SKILL.md:139
Ruby/shell backtick execution
> **Note**: You must be on `main` to run `bauplan branch merge`. The branch name is printed by the W
The note reinforces running a Bauplan CLI merge from main. It is not shell injection evidence, but it confirms the skill includes external command usage for publishing.

Risk Factors

⚙️ External commands (35)
SKILL.md:15 SKILL.md:19 SKILL.md:21 SKILL.md:27 SKILL.md:30 SKILL.md:31 SKILL.md:33 SKILL.md:34 SKILL.md:40-50 SKILL.md:50-56 SKILL.md:56-57 SKILL.md:57 SKILL.md:58-59 SKILL.md:59-60 SKILL.md:60-61 SKILL.md:61-62 SKILL.md:62-63 SKILL.md:63-64 SKILL.md:64-65 SKILL.md:65-73 SKILL.md:73-81 SKILL.md:81-86 SKILL.md:86-91 SKILL.md:91-94 SKILL.md:94-99 SKILL.md:99-102 SKILL.md:102-106 SKILL.md:106-110 SKILL.md:110 SKILL.md:112-120 SKILL.md:120-126 SKILL.md:126-128 SKILL.md:128-137 SKILL.md:137-139 SKILL.md:139
🌐 Network access (1)
SKILL.md:67
Audited by: codex View Audit History →
Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report
Security Assessment

Copy report link

https://skillstore.io/skills/bauplanlabs-wap-ingestion/audits/10?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/bauplanlabs-wap-ingestion/security.svg)](https://skillstore.io/skills/bauplanlabs-wap-ingestion?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/bauplanlabs-wap-ingestion?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/bauplanlabs-wap-ingestion/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/bauplanlabs-wap-ingestion.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>
Academic citations (APA · BibTeX · CFF)

APA citation

BauplanLabs. (2026). wap-ingestion security audit report (audit version 10) [Author version unspecified]. Skillstore. https://skillstore.io/skills/bauplanlabs-wap-ingestion/audits/10

BibTeX citation

@techreport{bauplanlabs-bauplanlabs-wap-ingestion-2026, author = {BauplanLabs}, title = {wap-ingestion security audit report (audit version 10)}, institution = {Skillstore}, year = {2026}, number = {10}, url = {https://skillstore.io/skills/bauplanlabs-wap-ingestion/audits/10}, note = {Author version unspecified} }

CITATION.cff

cff-version: 1.2.0 message: "If you use this Skill, cite its author and this versioned security audit report." title: "wap-ingestion security audit report (audit version 10)" version: "unspecified" type: report authors: - name: "BauplanLabs" date-released: "2026-07-09" url: "https://skillstore.io/skills/bauplanlabs-wap-ingestion/audits/10" identifiers: - type: other value: "skillstore:bauplanlabs-wap-ingestion:audit:10" description: "Skillstore immutable audit report identifier"

Skillstore Score

Why this score Evidence Confidence: High
55
Architecture
85
Maintainability
87
Content
70
Community
83
Spec Compliance

What You Can Build

Load a New S3 Dataset

Create a temporary Bauplan branch, ingest S3 files, and inspect row counts before publication.

Append to an Existing Table

Use the existing table path to import new S3 rows while keeping changes isolated on a branch.

Review a Controlled Publish

Keep the branch open after ingestion so a reviewer can inspect data before merging to main.

Try These Prompts

Start a Basic WAP Ingestion 
Help me ingest data from this S3 path into a new Bauplan table using WAP. Ask me for any missing required inputs first.
Prepare an Inspect-Only Load 
Create a WAP ingestion script for my S3 dataset. Use inspect on success and keep the branch on failure.
Append Data with Extra Checks 
Adapt the WAP flow to append S3 data to an existing Bauplan table. Add audit checks beyond row count before publish.
Plan a Multi-Table Publish 
Design a WAP ingestion workflow for multiple related Bauplan tables. Keep all changes on one branch and explain the publish decision points.

Best Practices

  • Keep the default inspect behavior until a human has reviewed the imported data.
  • Add dataset-specific quality checks before allowing a merge to main.
  • Use clear table names and branch names so reviewers can trace the ingestion source.

Avoid

  • Do not merge to main before validating row counts and expected schema behavior.
  • Do not delete failed branches when they are needed for debugging or audit evidence.
  • Do not reuse the template without replacing example S3 paths and table names.

Frequently Asked Questions

What does WAP mean in this skill?
WAP means Write-Audit-Publish. The data is written to a branch, checked, and then published only after review.
Does this skill publish data to main automatically?
The default behavior keeps the branch open for inspection. Automatic merge is only used when the user selects that behavior.
What file sources are covered?
The instructions focus on S3 URI patterns for formats such as parquet, CSV, and JSONL files.
Can I use this for an existing table?
Yes. The skill explains an append path that skips table creation and imports data into an existing table on a branch.
What audit checks are included?
The template verifies that imported row count is greater than zero. Users should add checks for their data contract.
Which AI coding tools can use this skill?
The report lists support for Claude, Codex, and Claude Code.

Developer Details

License

MIT

Skillstore revision

r1

Version notice

The author did not declare a version.

Repository

https://github.com/BauplanLabs/bauplan-mcp-server/tree/main/skills/wap

Ref

26421118b848d9f1efc0aa169d8a7a9e7e0a877e

Maintenance freshness

7/21/2026

Usage

4 downloads · 198 views

File structure

📄 SKILL.md

📄 wap_template.py