sirikit
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [Prompt Injection] (SAFE): The content consists of standard technical documentation and code snippets for Swift/iOS development. No override markers or jailbreak attempts were found.
- [Data Exposure & Exfiltration] (SAFE): No hardcoded credentials or sensitive file paths were detected. The snippets use generic identifiers (e.g., 'order-123') and sample App Group identifiers.
- [Obfuscation] (SAFE): Text is clear and legible. No Base64, zero-width characters, or homoglyphs are present.
- [Unverifiable Dependencies] (SAFE): The skill contains no package manager files (package.json, requirements.txt) and does not attempt to install or execute remote scripts.
- [Indirect Prompt Injection] (SAFE): While the skill describes handling user-input data from Siri intents (e.g., 'OrderSoupIntent'), it does not define any agentic tools that could be exploited via these inputs within the context of an AI agent's execution environment. It is strictly educational documentation.
- [Persistence & Privilege Escalation] (SAFE): No commands related to system persistence or unauthorized privilege elevation were found.
Audit Metadata