research-market
Warn
Audited by Snyk on Jul 4, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). At runtime, the skill’s competitor/trends/consumer research agents fetch and scrape public web pages and community posts (outsider-authored free text) via WebSearch/Exa/Firecrawl, which the agents then ingest into the LLM context to produce the competitive landscape and user sentiment.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata