testland/ai-test-generator
Generates tests from natural-language specs (acceptance criteria, user stories, requirements) using an LLM, with confidence scoring per test case (LLM self-assessment plus heuristics: assertion quality, naming, completeness), batching uncertain cases for human review, and integration with the team's existing test framework. Use when the user asks to generate unit tests from acceptance criteria, convert user stories to test cases, automate test creation from requirements, or augment a spec-driven test suite with AI-generated stubs that are then curated before merge.
72
90%
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 Step 1/Step 2 reads the provider-user-supplied spec/AC text (e.g., input YAML like `acceptance_criteria[].description` and `inputs/expected`) and passes it verbatim into the LLM via `scripts/ai-gen.py` (`messages` user content), so an outsider can submit poison text through whatever mechanism supplies that input to the workflow.
Where we found it
input YAML acceptance criteria (acceptance_criteria[].description, inputs, expected)
content-type · 6 sites
The plugin reads provider-user-supplied acceptance criteria text from input YAML and passes it verbatim into the LLM's user message, enabling indirect prompt injection by anyone who controls the spec input.
- Audited
- Security analysis