skills/muxinc/skills/mux-video/Gen Agent Trust Hub

mux-video

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [Safe Documentation] (SAFE): The analyzed files consist of reference guides and implementation examples for Mux Video and Data APIs. No executable malicious scripts or prompt injection instructions are present.
  • [Standard Dependency Usage] (SAFE): The documentation references official packages such as @mux/mcp and sanity-plugin-mux-input. These are legitimate libraries provided by the Mux organization for platform integration.
  • [Indirect Prompt Injection Surface] (LOW): The MCP server documentation (reference/mcp-server.md) describes a tool that ingests external data (video metadata, analytics) from the Mux API. This creates a standard surface for indirect prompt injection if an attacker controls the data within the Mux account, though the documentation itself contains no malicious instructions.
  • Ingestion points: Mux API (Video metadata, Asset titles, Analytics metrics)
  • Boundary markers: Not explicitly defined in documentation examples; assumed to be handled by the LLM client.
  • Capability inventory: Asset management, metadata updates, analytics querying.
  • Sanitization: Not present in documentation examples; relies on Mux API and LLM client sanitization.
  • [Credential Safety] (SAFE): All examples use clearly labeled placeholders (e.g., your-access-token-id, YOUR_ENV_KEY_HERE) rather than hardcoded credentials.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:36 PM