customer-research
Warn
Audited by Snyk on Jun 14, 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 skill’s runtime workflow includes “Tier 4 — External Sources: Web search… Public knowledge bases, help centers, release notes, Third-party documentation,” which can ingest outsider-authored free text from fetched web pages into the LLM context during synthesis.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata