conference-speaker-scraper

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The code routes Apify calls (and any provided token) through an undocumented gooseworks.ai proxy and requires an environment API key (GOOSEWORKS_API_KEY), which results in user API tokens and scraped data being sent to a third party — high risk of credential/data exfiltration.

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

• Third-party content exposure detected (high risk: 0.85). Yes—required runtime workflow fetches outsider-authored free text from a user-supplied public URL (--url) via requests.get(...).text and then parses/prints extracted bios/names into the agent’s context (direct mode HTML scraping path).