ml-kit-genai-prompt-api

Pass

Audited by Gen Agent Trust Hub on Sep 7, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides instructional content for using official Android ML Kit libraries (com.google.mlkit:genai-prompt, com.google.mlkit:genai-schema-compiler). All external resources and documentation links point to trusted domains owned by Google (developer.android.com, ai.google.dev, cloud.google.com).
  • [INDIRECT_PROMPT_INJECTION]: The skill documents techniques to handle untrusted user input within prompts. It specifically recommends using paired XML/HTML delimiters (e.g., <email>[content]</email>) to isolate user data from instructions, which is a recommended security practice to mitigate prompt injection risks.
  • [REMOTE_CODE_EXECUTION]: No remote code execution patterns were detected. The skill references standard Android build-time dependencies and the KSP (Kotlin Symbol Processing) plugin for generating structured output schemas, which is normal development behavior for the stated platform.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 7, 2026, 01:38 PM
Security Audit — agent-trust-hub — ml-kit-genai-prompt-api