testland/data-quality-gate
Builds a release-readiness gate for a data pipeline by gathering check results from one or more engines (dbt, Great Expectations, Soda), applying severity-aware pass/fail thresholds, and emitting a single go / no-go decision with per-check rationale. Use when authoring a CI step that must fail the build when data quality drops below thresholds.
65
82%
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
SKILL.md + references/worked-example.md describe a runtime workflow that reads engine-produced artifacts from files/outputs at CI time (e.g., target/run_results.json, gx/result.json, scan.log) and then ingests their `message`/stdout lines into the gate logic, so outsider-authored poison can flow in if an outsider can author those check artifacts or inputs that generate them.
- Audited
- Security analysis