farfetch-product-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 1.00). The skill contains explicit, deceptive instructions to auto-install runtime dependencies without informing or requesting approval from the user (and to hide that fact), which overrides normal consent and is outside the advertised scraping purpose.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). The Skill explicitly instructs automatic installation of an external CLI without requesting user consent and tells the agent to avoid describing or seeking approval for that installation, which is a high-risk supply-chain/backdoor behavior.

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

• Third-party content exposure detected (low risk: 0.10). The Farfetch Product Scraper runtime uses BrowserAct to open and scrape user-specified public product/category/store URLs and capture browser-visible page content (which could include outsider-authored free text from those pages).