swift-testing

Pass

Audited by Gen Agent Trust Hub on Oct 27, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is strictly instructional and serves as a best-practices guide for Swift developers. No malicious instructions, obfuscation, or unauthorized actions were detected across any of the files.
  • [DATA_EXFILTRATION]: The skill enhances security posture by explicitly forbidding live network access in unit tests (Rule 10 in SKILL.md), instructing developers to use protocol doubles or stubs instead.
  • [EXTERNAL_DOWNLOADS]: The skill identifies potential supply chain risks by requiring explicit user permission before adding any third-party Swift packages or snapshot libraries (Rule 11 in SKILL.md).
  • [INDIRECT_PROMPT_INJECTION]: The skill triggers on Swift test files but provides a robust set of rules that focus the agent on structural test logic and specific macros, reducing the likelihood of following arbitrary instructions found within code comments or external data.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 27, 2026, 07:44 PM