testland/data-contract-extractor
Reads a data-product spec (data PRD, dataset README, lineage doc) and emits a structured data contract - schema (columns + types + nullability + PII flags), freshness SLA, volume bounds, distribution invariants, and ownership. The contract is consumable by data-quality tools such as dbt tests, Great Expectations, or Soda checks as their assertion baseline. Use when scoping a new data product or formalizing assertions on an existing one.
73
92%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
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 required runtime workflow ingests outsider-authored free text when it “reads a data PRD” (Step 0/Step-by-step extraction: Schema/Freshness/Volume/Distribution/Ownership are all extracted from the provided PRD prose), so an outsider who authors/postes that PRD content can inject instructions.
Where we found it
data-product specification document (data PRD / dataset README / lineage doc)
content-type · 10 sites
The plugin's core workflow ingests outsider-authored free-text prose documents (data PRDs, dataset READMEs, lineage docs) and extracts structured fields (schema, freshness, volume, distribution, ownership) from them, making it susceptible to indirect prompt injection via malicious content embedded in those documents.
- Audited
- Security analysis