competitor-signals

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

• Third-party content exposure detected (high risk: 0.85). Yes—at runtime the required workflow fetches outsider-authored free text from public sources (Product Hunt comments/bodies via the PH GraphQL API and/or Apify scraper, and Hacker News comment text via Algolia), which the script places into the context field and then into the produced CSV for downstream LLM analysis.

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

• Potentially malicious external URL detected (high risk: 0.90). The script starts and polls Apify actors via a Gooseworks proxy (APIFY endpoints built from GOOSEWORKS_API_BASE) — e.g., it contacts https://app.gooseworks.ai to launch remote Apify runs, which executes remote actor code at runtime.