pricing-page-psychology-audit

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

• Third-party content exposure detected (high risk: 1.00). The skill's scraper (scripts/scrape_pricing.py) fetches and parses arbitrary user-provided http/https SaaS pricing page URLs and returns the full page text which the SKILL.md/README instruct the AI to analyze and use to generate actionable rewrites and recommendations, directly exposing the agent to untrusted third-party content that could contain malicious instructions.

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 an arbitrary user-provided pricing page URL (e.g., https://linear.app/pricing) and outputs the full page text to be fed into the AI, meaning remote content retrieved at runtime directly controls the model's prompts/analysis.