product-name-extractor
Warn
Audited by Snyk on Aug 8, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). [SKILL.md: Workflow step “1. Read Text” states the agent “Receive[s] any text provided by the user… (product descriptions, articles, lists, conversations, etc.)”, which is outsider-authored free text that the LLM must ingest to perform extraction.]
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata