swiftui-layout-components
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEMETADATA_POISONINGINDIRECT_PROMPT_INJECTION
Full Analysis
- [METADATA_POISONING]: The skill provides instructions and examples for a non-existent version of iOS (referenced as "iOS 26") and includes documentation links to a third-party domain (
sosumi.ai) instead of official Apple resources. This deceptive content could mislead the AI agent into generating hallucinated code or assuming the presence of features that do not exist in current development environments. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and review user-provided screen descriptions and UI requirements, creating an attack surface for indirect prompt injection.
- Ingestion points: Screen descriptions and layout requirements provided by the user in natural language (seen in
evals/evals.json). - Boundary markers: The skill lacks explicit instructions for the agent to use delimiters or ignore potentially malicious instructions embedded within the user's UI descriptions.
- Capability inventory: The skill does not currently define tools for network access, file writing, or command execution, which limits the potential impact of an injection.
- Sanitization: There is no requirement for the agent to sanitize or validate the incoming UI data before generating layout recommendations.
Audit Metadata