relevancekit

Pass

Audited by Gen Agent Trust Hub on Sep 11, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill offers standard Swift programming guidance for Apple's RelevanceKit framework. The logic and framework usage align with legitimate developer practices.\n- [EXTERNAL_DOWNLOADS]: Links to documentation on sosumi.ai are included as references in SKILL.md. These are static informational links and do not involve remote code execution or automated downloads.\n- [INDIRECT_PROMPT_INJECTION]: The skill identifies external documentation as a source, creating a theoretical ingestion surface. 1. Ingestion points: SKILL.md references; 2. Boundary markers: Absent; 3. Capability inventory: Code snippet generation; 4. Sanitization: Absent. The risk is considered minimal as it only involves user-facing documentation links.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 11, 2026, 11:14 AM
Security Audit — agent-trust-hub — relevancekit