engage-sdk-integration
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is intended for integration assistance and does not contain any malicious patterns. All identified potential threat surfaces are assessed as safe according to the specific rules for this analysis skill.
- [COMMAND_EXECUTION]: The skill instructs the agent to run Gradle build commands (e.g.,
./gradlew assembleDebug --no-daemon) to verify code generation. These are standard development verification steps and use the--no-daemonflag as recommended for sandbox environments. - [INDIRECT_PROMPT_INJECTION]: The workflow requires the agent to ingest developer-provided data models and schemas to generate mapping code. This ingestion is central to the skill's primary purpose and lacks any intent to bypass safety guidelines.
- [EXTERNAL_DOWNLOADS]: The skill provides a link to download an official verification app from Google's trusted domain (
dl.google.com). Per the security rules, downloads from trusted organizations are considered safe and do not escalate the verdict. - [DEPENDENCIES]: All referenced Android libraries (e.g.,
com.google.android.engage) and Gradle plugins are standard packages from trusted repositories.
Audit Metadata