multimodal-embedding-serving-user

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches deployment scripts (setup.sh) and configuration files (compose.yaml) from the official Open Edge Platform GitHub repository. These downloads are necessary for the service setup and originate from the vendor's own infrastructure.
  • [COMMAND_EXECUTION]: Instructs the agent to run standard Docker Compose and shell commands to start and manage the microservice. These commands are typical for local container deployment and do not involve privilege escalation.
  • [DATA_EXFILTRATION]: Network operations are restricted to communication with the local service on localhost:9777 and fetching assets from trusted domains (GitHub and Intel's sample video repository). No sensitive local data is accessed or transmitted externally.
  • [REMOTE_CODE_EXECUTION]: The skill downloads and sources a setup.sh script from the author's repository. This is a standard deployment pattern for this microservice and, as the source is the verified vendor, it is considered safe in this context.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 04:38 PM
Security Audit — agent-trust-hub — multimodal-embedding-serving-user