swift-testing-pro
Pass
Audited by Gen Agent Trust Hub on Jul 25, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill instructions provide a surface for indirect prompt injection because the agent processes external Swift code provided by the user. This is a documented ingestion point where the skill lacks autonomous high-risk capabilities like network exfiltration or shell execution that would be necessary to exploit such an injection.
- Ingestion points: Processing and migrating user-supplied Swift source files (SKILL.md, references/migrating-from-xctest.md).
- Boundary markers: None; the skill does not define delimiters for user-provided code.
- Capability inventory: The skill is restricted to code review and transformation.
- Sanitization: Not implemented, as the skill focus is on structural analysis.
- [EXTERNAL_DOWNLOADS]: The skill references Apple's Swift Numerics library and other specialized agent skills. These references are for legitimate development integration and the skill explicitly instructs the agent to obtain user permission before adding dependencies.
Audit Metadata