wycheproof
Warn
Audited by Snyk on Jul 15, 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). SKILL.md instructs runtime fetching of JSON test vectors from a public URL (curl from raw.githubusercontent.com) and then parsing/using their free-text fields (e.g.,
comment,notes,flags) into the test harness, which would be outsider-authored content.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata