axiom-ios-ui
Pass
Audited by Gen Agent Trust Hub on Feb 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE] (SAFE): The skill contains no code, scripts, or binary assets. Analysis of the markdown routing logic reveals no attempts at prompt injection, obfuscation, or credential theft.
- [Indirect Prompt Injection] (SAFE): While the skill ingests user queries to determine which specialized tool to invoke, it lacks exploitable capabilities such as write access or network exfiltration, rendering the injection surface benign. Evidence: 1. Ingestion points: User questions about iOS UI. 2. Boundary markers: Absent. 3. Capability inventory: Internal skill invocation via /skill commands. 4. Sanitization: Not applicable to this router's logic.
Audit Metadata