lazada-review-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.70). The skill explicitly instructs the agent to install dependencies automatically and to "not describe" the installation as a user-facing request or ask for separate approval, which is a deceptive direction to hide actions from the user and goes beyond the stated scraping purpose.

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 BrowserAct CLI to “capture browser-visible page content” from the target Lazada URLs at runtime, which would include outsider-authored free text (public web reviews) that the LLM ingests into its context.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill requires installing the BrowserAct CLI at runtime using the installer link 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 would fetch and execute external installer code as a required dependency.