The Agent Skills Directory

[SAFE]: No security threats were identified. The skill provides legitimate guidance for unit testing and uses standard tools like @pinia/testing and Vitest. No obfuscation, unauthorized network calls, or persistence mechanisms were found.\n- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it ingests and reviews user code (SKILL.md). Ingestion points: External Vue components, composables, and Pinia stores are provided to the agent for review. Boundary markers: Absent (the skill does not explicitly instruct the agent to ignore instructions embedded in the input code). Capability inventory: The skill is restricted to generating text and test code within the response. Sanitization: None mentioned. The risk is considered negligible as the skill lacks dangerous tools or execution capabilities.

unit-test-vue-pinia