The Agent Skills Directory

[SAFE]: The skill provides a robust set of architectural guidelines and code references for Vue 3 development, emphasizing security-conscious patterns like the Composition API, strict TypeScript typing, and proper resource cleanup.
[EXTERNAL_DOWNLOADS]: Documents the configuration and use of numerous well-known Node.js packages and plugins (e.g., Nuxt, Pinia, Quasar, and Sentry). All external resources originate from established technology vendors or official community repositories and are documented neutrally as part of standard development setup.
[PROMPT_INJECTION]: The skill includes a 'SAFETY GUARD' section that explicitly instructs the agent to treat reference snippets as examples and to require human confirmation before performing any production-impacting actions, which serves as a significant deterrent against accidental or malicious execution.
[PROMPT_INJECTION]: Evaluated the surface for indirect prompt injection (Category 8):
Ingestion points: The skill processes natural-language requirements and user-provided feature descriptions in SKILL.md.
Boundary markers: No specific delimiters are defined to isolate user-provided data from the agent's internal logic during code generation.
Capability inventory: The skill generates application code, build configurations, and architectural plans.
Sanitization: There are no explicit instructions for sanitizing or validating user-provided requirements before they are reflected in the generated output.
Note: This surface is inherent to the primary purpose of a coding assistant skill and is mitigated by the agent's safety constraints.
[CREDENTIALS_UNSAFE]: Promotes secure management of sensitive data (such as API endpoints and authentication tokens) by demonstrating the use of environment variables and providing code templates that use safe placeholders rather than hardcoded secrets.

vue-expert