gemini-interactions-api

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references official Google SDKs (google-genai and @google/genai) for interaction with the Gemini API. These are well-known, legitimate packages from a trusted organization.
  • [COMMAND_EXECUTION]: Provides instructions for using the gcloud CLI tool to authenticate and enable cloud services, which is a standard administrative task for setting up Google Cloud environments.
  • [DATA_EXFILTRATION]: Demonstrates communication with official Google Cloud API endpoints (aiplatform.googleapis.com). This network activity is necessary for the skill's functionality and targets a trusted service.
  • [INDIRECT_PROMPT_INJECTION]: The skill enables the agent to send user-provided strings to the Gemini API, which is a standard attack surface for indirect prompt injection. However, this is the intended and primary purpose of the skill. 1. Ingestion points: input parameter in client.interactions.create calls (SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: Network communication with Google APIs (SKILL.md). 4. Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 05:40 AM
Security Audit — agent-trust-hub — gemini-interactions-api