amazon-keyword-tracker

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

• Third-party content exposure detected (high risk: 0.75). The skill’s runtime workflow for “SERP analysis” and “real-time monitoring” implies fetching/processing Amazon search results (organic/sponsored/featured content) and competitor listings, which are outsider-authored web page text that can be ingested into the agent’s LLM context as free-form SERP content.

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

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