research

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

• Third-party content exposure detected (high risk: 0.90). The skill's workflows explicitly fetch and ingest arbitrary public third‑party content (e.g., WebFetch/WebSearch, fabric -y for YouTube in Workflows/YoutubeExtraction.md and Fabric.md, BrightData scrape_as_markdown and Apify actors in Workflows/Retrieve.md and WebScraping.md, plus WebFetch/WebSearch calls referenced throughout SKILL.md and ExtractAlpha.md), require the agent to read/interpret those pages/transcripts as part of the research/synthesis workflow, and then use those findings to drive tool use and decisions—creating a clear avenue for indirect prompt injection.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly invokes fabric -y with user-supplied YouTube URLs (e.g., https://www.youtube.com/watch?v=VIDEO_ID or https://youtu.be/VIDEO_ID) at runtime to fetch transcripts that are injected into the agent's analysis prompts, meaning external content can directly control model inputs and behavior.