link-prospecting-research
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 workflow is a link-prospecting research pass that instructs the agent to “review competitor backlink patterns,” “find list-scrape sources,” and “expand seeds with autocomplete,” which at runtime typically requires fetching/searching external web results and/or ingesting scraped page text from outsider-authored sources into the LLM context (e.g., public search results, scraped lists, autocomplete-derived pages).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata