hallmark
Warn
Audited by Snyk on Oct 15, 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). The hallmark skill includes a
hallmark study <URL>verb (Branch B104 and Skill definition at lines 148, 597) that invokes WebFetch on random external URLs supplied by the user, reading their HTML and CSS as untrusted runtime data.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata