mobile-developer

Pass

Audited by Gen Agent Trust Hub on Feb 20, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE] (SAFE): No malicious patterns, such as prompt injection, obfuscation, or data exfiltration, were detected in the skill definitions.
  • [Indirect Prompt Injection] (LOW): The skill provides a surface for processing untrusted data (user-provided mobile code and tasks), which is a characteristic of this category.
  • Ingestion points: User-provided code snippets, project requirements, and task descriptions for mobile apps.
  • Boundary markers: Absent; there are no specific instructions to use delimiters for external data.
  • Capability inventory: None; the skill is purely instructional and does not define automated tools, script execution, or file writing within the provided SKILL.md.
  • Sanitization: Absent; the skill does not specify validation or escaping of user input before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 20, 2026, 08:03 PM