video-data

Pass

Audited by Gen Agent Trust Hub on Jul 31, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted user-generated content from YouTube, which serves as a potential vector for indirect prompt injection.\n
  • Ingestion points: Data is retrieved from YouTube video metadata, search results, and subtitles through the Oxylabs API endpoints described in SKILL.md and examples.md.\n
  • Boundary markers: No specific delimiters or instructions are used to separate external content from the agent's internal operational context.\n
  • Capability inventory: The skill possesses the capability to write files to the local file system using yt-dlp and perform network operations via curl, requests, and axios.\n
  • Sanitization: The retrieved content is directly used or printed without sanitization or validation in the provided code examples.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 31, 2026, 12:55 PM
Security Audit — agent-trust-hub — video-data