testland/gherkin-from-stories
Converts requirements in any input shape into Gherkin scenarios - a user story ("As a … I want … so that …"), a signed-off acceptance-criteria list (ATDD: @AC-N-tagged scenarios, NotImplementedError step stubs, AC-to-test traceability table), existing manual test steps (declarative rewrite that strips UI mechanics), or a raw spec / PRD section (acceptance-criteria extraction with Gherkin or plain-list output). Maps criteria to Scenario blocks, detects Scenario Outline opportunities, factors shared Background, reuses the curated step library, and flags implicit preconditions instead of fabricating them. Emits Gherkin (plus stubs in ATDD mode): runner detection and full step wiring belong to bdd-scenario-author. Use whenever requirements text of any shape needs to become a .feature file.
70
88%
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 workflow ingests “requirements text of any shape” directly as user-provided input (e.g., story/AC list/manual steps/raw PRD) and converts it into Gherkin, so outsider-authored free text can be posted for the LLM to process without selecting a specific trusted item first.
Where we found it
requirements text (user story / AC list / manual test steps / raw PRD)
content-type · 8 sites
The plugin accepts arbitrary free-form text as input ("requirements text of any shape") from four input channels — user stories, AC lists, manual test steps (including TestRail/Qase/Xray exports), and raw PRD sections — and processes it through the LLM to generate Gherkin, creating an indirect prompt injection surface.
- Audited
- Security analysis