NYC

axiom-ios-ui

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • Indirect Prompt Injection (LOW): The skill is designed to interpret user input and route it to other specialized skills or automated agents (e.g., axiom-swiftui-nav, swiftui-performance-analyzer). This pattern establishes a surface where untrusted data influences tool selection and execution.
  • Ingestion points: Natural language input from the user processed through the Routing Logic and Decision Tree defined in SKILL.md.
  • Boundary markers: None. The skill does not implement delimiters or instructions to ignore embedded commands within the user input.
  • Capability inventory: The skill can trigger other agent skills via the /skill command and launch independent automated agents for auditing tasks.
  • Sanitization: No sanitization, escaping, or validation logic is present for the input before routing actions are determined.
  • General Security Posture (SAFE): The skill does not contain hardcoded credentials, obfuscated code, network exfiltration patterns, or unauthorized file system access. It serves exclusively as a navigational coordinator for iOS development tasks.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:10 PM