market-finder

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.85). In Discovery/Audit mode the skill runs runtime web/marketplace discovery via nimble agent run / nimble search (e.g., Google Maps/Yelp/BBB pages and SERP snippets), which are outsider-authored free text that can be extracted and inserted into the agent’s LLM context for parsing/dedup/enrichment.