playbook-company-name-cleaning
Warn
Audited by Snyk on Aug 23, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). In the Clay toggle build, outsider-provided lead fields
{{RawCompanyName}}(and optional{{BareDomain}}) are passed at runtime into the GPT-4o-mini locked prompt as the user message (name="<raw company string>" domain="<bare lowercase domain, no www>"), so the LLM directly ingests free text originating from the user’s submitted/maintained lead data.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata