ios-chatbot-skill

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill directs the agent to build the application scheme and run tests using the project's existing toolchain, including Xcode, Tuist, or XcodeGen commands as appropriate for the environment.
  • [EXTERNAL_DOWNLOADS]: The workflow involves adding a dependency to the GenericChatbot library from the author's official GitHub repository (https://github.com/Erikote04/ios-generic-chatbot.git) using standard package managers like SwiftPM.
  • [PROMPT_INJECTION]: The skill implements an architecture that ingests application-specific data through a knowledge adapter.
    • Ingestion points: ChatKnowledgeSource adapter defined in reference/knowledge-errors-and-privacy.md.
    • Boundary markers: The instructions explicitly state that retrieved text should be treated as untrusted data.
    • Capability inventory: The skill performs file system modifications to project manifests and executes build/test scripts.
    • Sanitization: The documentation includes requirements to redact private content from logs and use normalized error reporting to avoid leaking diagnostics.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 10:46 AM
Security Audit — agent-trust-hub — ios-chatbot-skill