bansos-add-entry
Warn
Audited by Snyk on Jun 13, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). The required workflow step “Read the source page or user-provided evidence before writing copy” implies the agent may fetch and ingest outsider-authored free text from a runtime-supplied URL/page (public web content) into the LLM context for summarization/validation.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata