The Agent Skills Directory

[SAFE]: The skill serves as a technical reference for Swift developers, providing code examples and migration rules for the Swift Testing framework. All content is pedagogical and consistent with official documentation.
[SAFE]: No instances of prompt injection, data exfiltration, or malicious obfuscation were identified. The code snippets use dummy data and standard environment checks for CI/CD detection.
[SAFE]: Documentation regarding exit testing and subprocess management correctly describes framework-level APIs for testing crash conditions (ST-0012) and does not represent a security vulnerability.
[INDIRECT_PROMPT_INJECTION]: The skill possesses an ingestion surface for untrusted data as it is designed to review and migrate user-provided Swift code.
Ingestion points: User-supplied code and migration plans provided via prompt (referenced in evals/evals.json).
Boundary markers: Absent.
Capability inventory: The skill assists in writing and editing Swift files based on framework rules.
Sanitization: Absent.
This finding is assessed as safe due to the lack of unsafe interpolation or instructions that would cause the agent to execute untrusted content.

swift-testing