swiftui-patterns
Pass
Audited by Gen Agent Trust Hub on Aug 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to perform environment checks and filesystem modifications to set up a project environment.
- Evidence: SKILL.md contains instructions for the agent to "check whether the workspace is already inside a git repo with
git rev-parse --is-inside-work-tree" and to "rungit initat the project root". - Evidence: SKILL.md instructs the agent to "create one project-local
script/build_and_run.sh" for new app scaffolding. - [INDIRECT_PROMPT_INJECTION]: The skill directs the agent to process existing project source code, which constitutes an ingestion point for untrusted data.
- Ingestion points: SKILL.md directs the agent to "Read the nearest existing scene or root view before inventing a new desktop structure." in existing projects.
- Boundary markers: No specific delimiters or instructions are provided to help the agent distinguish between its core instructions and potentially adversarial content within the files it is asked to read.
- Capability inventory: The skill grants the agent capabilities to write files, create executable scripts, and run shell commands (git).
- Sanitization: There is no mention of sanitizing or validating the content of the files being read before the agent acts upon the information.
Audit Metadata