business-email-extractor

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

• Third-party content exposure detected (high risk: 0.75). The skill triggers a runtime deep crawl of Google Maps/business websites via gmapsscraper.io (email: true, depth: 2) and then downloads raw_results.csv, which will include free-form text scraped from third-party sites/pages (outsider-authored content) that the agent may read/parse into the LLM context.

MEDIUM W021: Hidden or invisible Unicode characters detected (potential obfuscation or prompt injection).

• Hidden Unicode characters detected (1 type(s) found)