deepstream-dev

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or security vulnerabilities were detected during the analysis of the skill's instructions and reference documentation.
  • [EXTERNAL_DOWNLOADS]: The skill references downloads from official and trusted sources, including NVIDIA's NGC registry ("nvcr.io", "api.ngc.nvidia.com") and official GitHub organizations ("github.com/NVIDIA-AI-IOT"). These are necessary for obtaining models and development tools and are documented neutrally.
  • [INDIRECT_PROMPT_INJECTION]: The skill documents surfaces for ingesting untrusted data (e.g., video URIs and RTSP streams) and provides capabilities to write files or send data to network brokers. However, these are inherent to the SDK's purpose as a video analytics tool. No exploitable vulnerabilities or missing sanitization patterns were identified beyond the standard SDK surface.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 08:38 AM
Security Audit — agent-trust-hub — deepstream-dev