ToolTrust
B15/100
NVIDIA-AI-Blueprints

video-search-and-summarization

mcp3.2.1

@NVIDIA-AI-Blueprints

NVIDIA AI Blueprint for video search and summarization (VSS) is a GPU-accelerated reference architecture for building video analytics agents with real-time verified alerts, visual Q&A, and automated reporting. The VSS Blueprint uses vision language models (VLMs) such as NVIDIA Cosmos, LLMs such as NVIDIA Nemotron, RAG, and NVIDIA NIMs.

By NVIDIA-AI-Blueprints | 28 findings | Scanned 7/28/2026 | tooltrust-scanner/v0.3.19 | 1.8k

1 High10 Low17 Info

Risk Summary

Safe With Normal Controls

Excessive Permissions is the main signal, but overall risk remains within an acceptable range.

Potential impact: The agent may gain overly broad access to files, network, databases, or execution capabilities.

Recommended action: No high-risk findings were detected in this scan, but you should still apply least-privilege defaults and rescan after changes.

Suggested policy: keep this tool behind manual approval, do not allow unattended runs, and re-scan after narrowing risky permissions.

Security Findings (28)

  • HighAS-012

    🔄Tool Drift

    Tool set changed silently at v3.2.1: 8 tool(s) added, 6 tool(s) removed without a version bump.

    + 8 added

    brave_image_searchbrave_llm_contextbrave_local_searchbrave_news_searchbrave_place_searchbrave_summarizerbrave_video_searchbrave_web_search

    − 6 removed

    create_summary_taskget_subtitleget_task_statussummarize_by_chaptersummarize_videosummarize_video_with_config

    Fix: The set of tools exposed by this server changed between scans of the same version — a sign the package was silently updated without a version bump. Audit the changelog and all tool definitions before trusting this server. Pin to a specific commit hash rather than a floating version tag.

  • LowAS-002

    ⚠️Excessive Permissions ×3

    input schema exposes 15 properties (threshold: 10)

    brave_web_search

    input schema exposes 14 properties (threshold: 10)

    brave_llm_context

    input schema exposes 13 properties (threshold: 10)

    brave_place_search

    Fix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.

  • LowAS-011

    ℹ️Missing Rate-Limit / Timeout ×7

    tool performs network or execution operations but declares no rate-limit, timeout, or retry configuration

    brave_web_searchbrave_news_searchbrave_image_searchbrave_video_searchbrave_local_searchbrave_llm_contextbrave_place_search

    Fix: Declare explicit rate-limit, timeout, and retry configuration for all network and execution tools. Implement exponential back-off and surface resource state to the calling agent.

  • InfoAS-002

    ⚠️Excessive Permissions ×7

    declared capabilities: network access

    brave_web_searchbrave_news_searchbrave_image_searchbrave_video_searchbrave_llm_context

    declared capabilities: network access, database access

    brave_local_searchbrave_place_search

    Fix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.

  • InfoAS-014

    ℹ️Dependency Inventory Unavailable ×8

    Tool did not expose metadata.dependencies or repo_url, so supply-chain coverage is limited.

    brave_web_searchbrave_news_searchbrave_image_searchbrave_video_searchbrave_local_searchbrave_llm_contextbrave_place_searchbrave_summarizer

    Fix: Review and remediate the identified issue.

  • InfoAS-010

    🔑Insecure Secret Handling ×2

    input parameter "maximum_number_of_tokens" accepts a credential (informational; not evidence of insecure handling)

    brave_llm_context

    input parameter "maximum_number_of_tokens_per_url" accepts a credential (informational; not evidence of insecure handling)

    brave_llm_context

    Fix: Avoid accepting raw credentials as input parameters. Use secret managers (e.g. 1Password CLI, AWS Secrets Manager) and ensure credentials are never logged or stored in agent traces.

Scan this tool yourself

Reproduce this audit locally, integrate into CI, or let your agent audit its own tools.

Install once, then scan any MCP server:

$ curl -sfL https://raw.githubusercontent.com/AgentSafe-AI/tooltrust-scanner/main/install.sh | bash
$ tooltrust-scanner scan --server "npx -y video-search-and-summarization"

Adjust the package name if your npm registry name differs from the tool ID. View source

Add badge to your README

Copy this Markdown to show your ToolTrust grade on GitHub.

[![ToolTrust Grade B](https://raw.githubusercontent.com/AgentSafe-AI/tooltrust-directory/main/docs/badges/grade-b.svg)](https://github.com/AgentSafe-AI/tooltrust-directory)