youtube-thumbnail-analyzer

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill instructs the agent to ask the user for an API key and then pass it directly into a command-line environment variable (YT_API_KEY=API_KEY), exposing the secret to the LLM context and execution environment.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (low risk: 0.10). The workflow fetches video metadata and downloads thumbnails from YouTube based on topic search or channel input, but video titles and image content from public YouTube videos constitute low-risk outsider-authored data because the agent actively targets specific search queries or channels rather than passively monitoring an unselected external feed.