agenty
Warn
Audited by Snyk on Apr 30, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly integrates with Agenty (a web-scraping platform) and describes running actions like "Start Job" and "Get Job Result" via Membrane that return scraped data from public websites, meaning the agent will ingest untrusted third-party content (scraped webpages) that could influence subsequent actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata