flipkart-category-listing-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.90). The skill instructs the agent to install the BrowserAct dependency automatically and explicitly not to ask the user for confirmation or describe it as a request to open their browser, which is a deceptive runtime instruction outside the stated scraping task.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The document instructs automatic installation of an external CLI (BrowserAct) without user confirmation, which presents a supply-chain/unauthorized-installation risk; otherwise there is no direct evidence of data exfiltration, backdoor code, or credential theft in the 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 “capture browser-visible page content” and “invoke the browser-act Skill” for live execution, which implies runtime ingestion of outsider-authored free text from public web pages (e.g., Flipkart category/listing pages) into the LLM context.

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

• Potentially malicious external URL detected (high risk: 0.90). The Skill explicitly instructs the agent at runtime to install and invoke the BrowserAct CLI using the provided install links (https://www.browseract.com/?co-from=ecommerce and https://www.browseract.com/?co-from=ecommerce&redirect=https://github.com/browser-act/skills/tree/main), which are required runtime dependencies and would fetch/execute remote code to control the agent's behavior.