physical-ai-people-attribute-search
Pass
Audited by Gen Agent Trust Hub on Jul 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Orchestrates physical-AI workflows using shell scripts and platform CLI tools like
osmoandkubectlfor setup, submission, and monitoring. - [COMMAND_EXECUTION]: Dynamically constructs execution arguments and configuration files at runtime using Python and shell scripts to manage per-sample augmentation parameters.
- [EXTERNAL_DOWNLOADS]: Performs network probes to the
nvcr.iocontainer registry for image verification and communicates with OpenAI-compatible model endpoints for inference tasks. - [PROMPT_INJECTION]: Ingests and processes user-provided image datasets through LLM and VLM models during the augmentation and labeling stages, representing an inherent vector for indirect prompt injection via data poisoning.
Audit Metadata