ios-app-workflow
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The workflow involves analyzing local project data and 'local agent instructions', which creates a surface for indirect prompt injection if the project files contain malicious content.
- Ingestion points: In
SKILL.md, theProject Preflightsection instructs the agent to inspect workspace files, Git status, and 'local agent instructions'. - Boundary markers: The skill does not define specific delimiters or instructions to disregard potentially adversarial content within these local files.
- Capability inventory: The skill coordinates code modifications and execution through testing frameworks and simulator tools (
swift-testing,ios-simulator). - Sanitization: There are no explicit instructions for sanitizing or validating project file content before it is processed by the agent.
Audit Metadata