macos-swiftui-patterns
Pass
Audited by Gen Agent Trust Hub on Jun 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill directs the agent to perform environment checks and repository initialization using standard version control tools. Evidence includes instructions in SKILL.md to run git rev-parse --is-inside-work-tree and git init when setting up a new project scaffolding.
- [PROMPT_INJECTION]: The skill's workflow involves reading and analyzing local application source code to determine the correct architecture for new components, which constitutes an indirect prompt injection surface. Ingestion points: Reads existing scenes, root views, and workspace structure (SKILL.md). Boundary markers: No explicit delimiters or warnings to ignore instructions within analyzed files are specified. Capability inventory: File creation, directory management, and shell command execution (git). Sanitization: No evidence of validation or filtering for content retrieved from existing project files.
Audit Metadata