The Agent Skills Directory

[DYNAMIC_EXECUTION]: The skill includes documentation examples that use the eval() function to execute strings as code within Vitest test suites. While this is used to demonstrate parameterized tests for calculator logic, the use of eval() is a risky practice if applied to untrusted inputs. Evidence: references/overview.md and references/vitest.md contain the code snippet expect(eval(input)).toBe(expected).
[INDIRECT_PROMPT_INJECTION]: The skill is designed to generate code and tests based on user requests, which creates a potential surface for indirect prompt injection. 1. Ingestion points: The skill triggers on user prompts to write tests or create a test as defined in SKILL.md. 2. Boundary markers: There are no explicit boundary markers or instructions to ignore embedded commands in the processed input. 3. Capability inventory: The skill documentation describes the use of shell-based test runners (pnpm pest, pnpm vitest, pnpm playwright) which execute code within the project environment. 4. Sanitization: No specific sanitization or filtering logic is provided for the data used to generate or populate tests.
[EXTERNAL_DOWNLOADS]: The skill references and provides commands for installing testing frameworks from official registries. Evidence: SKILL.md and reference files mention installing vitest, playwright, and pest using pnpm and composer. These are well-known and widely used development tools.

testing