Skills
Navigate
skills/dcc-mcp/dcc-asset-free-media/mixkit-free-assets/Gen Agent Trust Hub

mixkit-free-assets

Pass

Audited by Gen Agent Trust Hub on Sep 5, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes metadata such as titles and descriptions from Mixkit asset pages which are subsequently presented to the agent context.
  • Ingestion points: The utility script scripts/_mixkit.py fetches HTML content from mixkit.co to extract titles, authors, and descriptions for various assets.
  • Boundary markers: Extracted metadata is interpolated into AssetDescriptor objects without explicit boundary delimiters or instructions to ignore potential commands embedded within the text.
  • Capability inventory: The skill possesses file-writing capabilities via the download function in scripts/_mixkit.py, which uses urllib.request to save files to the local file system.
  • Sanitization: Basic HTML tag removal and unescaping are performed, but there is no specific filtering for natural language instructions that could influence the agent's behavior.
  • [EXTERNAL_DOWNLOADS]: The skill fetches free-license stock media and After Effects templates from Mixkit's official asset servers (assets.mixkit.co). This functionality aligns with the skill's stated purpose of providing free stock assets.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 5, 2026, 03:21 PM