earnings-attribution
Warn
Audited by Snyk on Jun 17, 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 workflow’s Step 4/5 explicitly ingests outsider-authored free text from runtime-fetched public news articles (via the
neo4j-newssubagent) and from Perplexity web search results (viamcp__perplexity__perplexity_search/ask/research), which can contain indirect prompt-injection content that the agent may include in its LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata