rag-architect

Warn

Audited by Snyk on Mar 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: 0.90). The SKILL.md ingestion pipeline explicitly instructs "Load: Extract text from PDF, HTML, Notion", indicating the skill ingests HTML (public web) content which the agent reads and uses as retrieved_chunks to drive RAG answers, so untrusted third‑party content could inject instructions.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 15, 2026, 07:17 PM
Issues
1