v0-app-prompt
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input such as application requirements and code context to generate output prompts, which represents an indirect injection surface. Ingestion points: User Input (Idea, Spec, Screenshot, or Code) as described in the Workflow & Composition section. Boundary markers: The skill uses Markdown structural headers for the output prompt but does not include explicit instructions for the model to ignore embedded commands in the source data. Capability inventory: None; the skill is configured with disable-model-invocation: true and has no access to shell, network, or file system tools. Sanitization: No input validation or sanitization steps are defined.
Audit Metadata