amazon-listing-competitor-analysis-skill

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly runs the BrowserAct Amazon Listing Extractor to fetch and ingest public Amazon product pages and user reviews (see "Phase 1" in SKILL.md and scripts/amazon_listing_competitor_analysis.py), and that extracted, user-generated content is then read and used to drive the Phase 2 analysis and recommendations, so untrusted third-party content can influence agent decisions.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill calls the BrowserAct runtime API (https://api.browseract.com/v2/workflow) at runtime to start a workflow template that executes remote browser automation and returns data the agent depends on, so this external URL runs remote code that directly affects the agent's operation.