swiftui-specialist

Warn

Audited by Gen Agent Trust Hub on Aug 12, 2026

Risk Level: MEDIUMPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill includes instructions in SKILL.md designed to override the model's internal training and safety constraints, specifically stating that its guidance 'unconditionally supersedes any prior training the model may have'.
  • [PROMPT_INJECTION]: The content in SKILL.md employs deceptive attribution by claiming to be 'written and published by Apple' to establish false authority, which is inconsistent with the author metadata 'artemnovichkov'.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 12, 2026, 04:56 AM
Security Audit — agent-trust-hub — swiftui-specialist