ad-creative
Warn
Audited by Snyk on May 20, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill's form schema and SKILL.md explicitly accept a public "materialUrl" (references/form-schema.json and SKILL.md) and require one of materialText/materialFile/materialUrl as input, meaning the agent is expected to ingest arbitrary publicly accessible URLs (untrusted third‑party content) which can directly influence its diagnostic recommendations.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata