create-knowledgebase
Warn
Audited by Snyk on May 20, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill explicitly accepts and ingests arbitrary HTTPS URLs into Bolna knowledgebases (see SKILL.md "Create from URL" and scripts/create_knowledgebase.py's --url option), meaning the agent will fetch and index untrusted public web content that can materially influence agent behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata