brand-voice-profiler

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

• Third-party content exposure detected (medium risk: 0.30). The skill’s runtime workflow explicitly scrapes and reads “2-3 real copy samples from the brand's website” (product/about/blog/email footer) via a web fetch/extraction fallback chain (WebFetch → Firecrawl → manual paste), so attacker-controlled free text can be ingested by posting/altering content on those pages/inputs the workflow fetches.