youtube-title-tag-optimizer

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly asks the agent to retrieve or prompt the user to "paste your" YouTube Data API v3 key and shows example CLI usage with the API key inline, which requires the LLM to receive and could cause it to emit the secret verbatim (high exfiltration risk).

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md (Step 3 and the included Python script) explicitly calls the YouTube Data API (search.list and videos.list) to fetch public, user-generated video titles, tags, and descriptions from YouTube and then analyzes that content to drive scoring, title generation, and recommendations, so untrusted third-party content is ingested and can materially influence the agent's outputs.