swiftui-responsive-layout
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill operates by analyzing user-provided SwiftUI code and layout diagnostic data, which presents a surface for indirect prompt injection.\n
- Ingestion points: The 'Diagnostic Workflow' in
SKILL.mdinstructs the agent to process view hierarchies and failure contexts provided by the user.\n - Boundary markers: There are no explicit instructions for the agent to use delimiters or ignore instructions embedded within the analyzed code.\n
- Capability inventory: The skill itself is instructional and does not possess capabilities to write to the file system or execute network requests.\n
- Sanitization: No sanitization or validation of the input data is described.\n- [EXTERNAL_DOWNLOADS]: The skill contains references to external documentation hosted on third-party domains.\n
- Evidence:
SKILL.mdlinks to multiple resources onhttps://sosumi.ai/for SwiftUI documentation mirrors.
Audit Metadata