vue-composition-api-best-practices
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and refactor user-provided Vue source code files (e.g.,
.vue,.ts). This establishes a surface for indirect prompt injection where malicious instructions could be embedded within the input code comments or string literals to influence the agent's refactoring logic. - Ingestion points: The agent is instructed to read and process user-supplied files, such as
messy-user-list.input.vue, as part of its core refactoring workflow. - Boundary markers: The skill utilizes specific Task Prompts (e.g., 'Use vue skill, refactor this Vue SFC to follow the project's Composition API best practices') to set the agent's context, but these act as weak boundaries against adversarial input code.
- Capability inventory: The skill's primary capability is source code generation and transformation. While the skill does not execute code itself, the output it produces is intended for integration into developer projects.
- Sanitization: The instructions do not define specific sanitization or validation steps for the input source code, relying instead on the agent's ability to maintain focus on the refactoring task.
Audit Metadata