quality-stack
Warn
Audited by Snyk on Apr 26, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill's Phase 1 workflow (SKILL.md and WORKFLOW.md) explicitly fetches research documents at runtime from public URLs (e.g., raw.githubusercontent.com/joaquimscosta/arkhe-claude-plugins/… via "WebFetch") and cross-references/uses those fetched docs to generate recommendations and drive setup decisions, so untrusted third-party content can influence the agent's actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata