pattern-creation
Warn
Audited by Snyk on Jul 22, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.65). SKILL.md Phase 1 explicitly takes the validated HTML template “from the conversation context” (user-pasted/referenced HTML) and then Phase 2–3 sends that template HTML to tools (
api_template_validate,api_imports_get), which means the LLM context includes outsider-authored free text provided by someone other than the operating user (e.g., pasted from another party) via the runtime HTML template.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata