pp-trendhunter

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

• Third-party content exposure detected (high risk: 0.90). The skill's CLI explicitly scrapes the public TrendHunter surface (RSS feed, sitemap, category and trend pages, search results) into a local corpus and the agent is instructed to read/extract FAQ Q&A, briefs, clusters, and scoring results that can materially drive follow-up actions, so untrusted third-party content can indirectly inject instructions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs installing and running remote code as a runtime dependency (e.g., via npx -y @mvanhorn/printing-press and go install github.com/mvanhorn/printing-press-library/library/marketing/trendhunter/cmd/trendhunter-pp-cli@latest), which fetches and executes external code required for the CLI.