skill-seekers-ref

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and ingests open web and user-generated sources (e.g., SKILL.md examples like "skill-seekers create https://react.dev" and references/cli-commands.md "scrape ", "video --url", "rss", "chat --platform slack/discord", and GitHub scraping), and those fetched pages are then analyzed/enhanced by the tool's AI pipeline (create/enhance/install steps), so untrusted third-party content can influence tool behavior and generated outputs.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill explicitly runs scraping/creation at runtime from documentation/GitHub URLs (e.g., "skill-seekers create https://react.dev"), and the fetched pages/repos are injected into the enhancement/LLM pipeline as model context to generate skill content, so external content can directly influence agent outputs.