echo-segment
Warn
Audited by Snyk on Jun 22, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). The skill ingests outsider-authored free text from support tickets and NPS verbatims (and potentially app store/G2 reviews) at runtime, which are user/customer-written quotes that the LLM would incorporate into persona cards under “WHAT THEY SAY”.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata