llm-red-team
Warn
Audited by Snyk on Sep 19, 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). The workflow in
SKILL.md(and its reference playbookguides/llm-red-team-playbook.md) requires the red-team agent to ingest and process arbitrary outsider-authored inputs (such as external PDFs, web pages, and chat/social feeds) during attack phases (like RAG poisoning and prompt injection testing).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata