ingest-article
Warn
Audited by Snyk on May 18, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill explicitly scrapes arbitrary public web pages using firecrawl (see "Workflow" step 2:
firecrawl scrape "$URL" --formats markdown -o ...) and ingests the returned untrusted page markdown/metadata into the agent's note workflow, exposing it to potential indirect prompt injection.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata