ea-intro-planner
Warn
Audited by Snyk on Jun 21, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). The skill’s runtime workflow ingests “Papers or documents: PDFs, pasted text, abstracts, URLs, excerpts” and then has subagents “Read the following source carefully” (including URLs/excerpts), so if the user supplies outsider-authored web content or documents, that free text is read and placed into the agent’s LLM context for topic extraction.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata