targeted-prospecting
Warn
Audited by Snyk on Jul 2, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.78). Yes—runtime calls to Scrapegraph/Tavily (public web search + scraping) and then “Extract & Deduplicate / Hiring signals / Competitive intel” can ingest scraped page text (outsider-authored) into the agent’s LLM context via the tool outputs (e.g.,
/v1/searchscraper,/v1/smartscraper, and/search), enabling indirect prompt injection.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata