niche-data-finder

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

• Third-party content exposure detected (high risk: 0.75). The skill’s workflow is to recommend external prospect data sources (e.g., regulatory directories, marketplaces, public datasets) and then extract their contents at runtime for evaluation/output, which would ingest outsider-authored free text from public web pages/directories into the agent’s LLM context.