pricing-page-psychology-audit

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

• Third-party content exposure detected (high risk: 1.00). This skill explicitly fetches and scrapes arbitrary public pricing pages (user-supplied URLs) — see SKILL.md Step 1/Step 2 and scripts/scrape_pricing.py (fetch_page + extract_all_text) — and the agent is required to read and act on that scraped page text to generate audits and rewrites, which could allow indirect prompt-injection from untrusted third‑party content.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill's runtime scraper fetches arbitrary user-provided HTTP(S) pricing pages (e.g., https://linear.app/pricing) and injects the scraped page text into the AI's analysis, so the external URL content directly controls the agent's prompts and is a required dependency.