improve-website
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 (low risk: 0.10). Source text ingestion happens only through user-provided inputs (e.g., pasted real assets/visitor evidence/URLs) in the skill’s intake (and then passed to phase skills), not from any outsider-authored feed/queue the workflow reads without selecting a specific item.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata