swiftui-audit
Pass
Audited by Gen Agent Trust Hub on Jul 11, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by design, as it is instructed to read and analyze external source files from a user's repository.
- Ingestion points: The agent is directed to discover and inspect SwiftUI view files, view models, and entry points within the codebase.
- Boundary markers: There are no specific instructions or delimiters provided to the agent to treat the content of the audited files as untrusted or to ignore instructions embedded within them.
- Capability inventory: The skill is restricted to reporting and does not have the ability to execute shell commands, perform network requests, or modify the filesystem.
- Sanitization: The instructions do not define any sanitization or validation logic for the code being ingested during the audit process.
Audit Metadata