youtube-thumbnails

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 embed it directly into a bash command invocation (YT_API_KEY=API_KEY python3 ...), exposing the secret value through the LLM context and output.

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

• Third-party content exposure detected (low risk: 0.10). The workflow fetches video titles and metadata from YouTube channels via the YouTube Data API and passes them to local JSON/Markdown files without direct LLM processing of untrusted body text.