gemini-interactions-java-api
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted user data via the
inputfield in theModelInteractionParamsandAgentInteractionParamsclasses as shown inSKILL.md. This creates a potential surface where malicious instructions in the input could influence the agent's behavior. - Ingestion points:
input()method calls in the Java examples. - Boundary markers: Not present; instructions and data are passed directly to the model parameters.
- Capability inventory: The skill enables network interactions with the Gemini API, including stateful cloud-managed conversations and remote agent execution.
- Sanitization: The provided examples do not demonstrate input sanitization or the use of delimiters to isolate user-supplied content.
- [EXTERNAL_DOWNLOADS]: The skill documentation guides the user to install the
io.github.glaforge:gemini-interactions-api-sdkdependency from Maven Central. This package is an official resource provided by the skill author.
Audit Metadata