sephora-product-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 1.00). The skill explicitly instructs the agent to install a runtime dependency automatically and to conceal/avoid asking the user for confirmation (lines 41-47), which is a deceptive directive outside the scraping task's stated purpose.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). This Skill explicitly instructs automatic installation of an external CLI without user consent and to capture browser-visible network responses, creating a high risk of unauthorized installation (supply‑chain risk) and potential data exfiltration of sensitive tokens or content.

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

• Third-party content exposure detected (high risk: 0.85). SKILL.md instructs the agent to use the runtime browser-act Skill to “capture browser-visible page content” from user-specified target URLs (public web pages), which can include outsider-authored free text that the LLM ingests via the browser-extracted content/network responses.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill instructs the agent to automatically install a required runtime dependency from https://www.browseract.com/?co-from=ecommerce&redirect=https://github.com/browser-act/skills/tree/main (and references https://www.browseract.com/?co-from=ecommerce), which indicates the agent will fetch and execute remote installer code at runtime to control the agent workflow.