swift-testing

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [Prompt Injection] (SAFE): The skill instructions focus on defining a strict output contract for code generation and do not contain patterns aimed at overriding safety filters or exfiltrating system prompts.
  • [Data Exposure & Exfiltration] (SAFE): No sensitive file access or hardcoded credentials were detected. The example credentials provided in the demonstration documentation are generic placeholders.
  • [Indirect Prompt Injection] (SAFE): The skill ingests user-provided scenarios to generate code, which is a standard surface for indirect prompt injection. However, given that the primary purpose of the skill is code generation for human review, the risk is minimal. (Ingestion points: User scenarios in SKILL.md; Boundary markers: Absent; Capability inventory: Swift code generation for tests and app-side ViewControllers; Sanitization: Absent).
  • [Remote Code Execution] (SAFE): The skill does not download or execute external scripts; it is limited to providing static Swift templates for local development.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:27 PM