ios-chatbot-skill
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides integration guidance for the GenericChatbot library. It emphasizes architecture preservation and standard development practices without introducing malicious commands or unauthorized access.
- [EXTERNAL_DOWNLOADS]: The skill references a remote dependency at
https://github.com/Erikote04/ios-generic-chatbot.git. This resource is owned by the skill's author (erikote04) and is managed through standard Swift Package Manager (SwiftPM) or Xcode workflows as part of the intended functionality. - [INDIRECT_PROMPT_INJECTION]: The skill defines an attack surface by ingesting external data via the
ChatKnowledgeSourceadapter. However, the documentation explicitly instructs the agent to treat retrieved text as untrusted and provides specific guardrails against leaking private content or credentials in logs. - [DATA_EXFILTRATION]: The instructions include robust privacy guardrails, explicitly forbidding the exposure of user prompts, generated messages, or credentials in diagnostics and logs.
Audit Metadata