aliexpress-search-by-image-reference-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.80). The skill instructs the agent to automatically install BrowserAct and explicitly tells it not to describe the installation as a request or ask the user for separate approval, which is a deceptive instruction about user-facing behavior outside the 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 access arbitrary live web pages/URLs at runtime and “capture browser-visible page content” (public web content), which can include outsider-authored free text that may be ingested into the LLM context.

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

• Potentially malicious external URL detected (high risk: 0.80). The Skill explicitly instructs the agent to "install" BrowserAct automatically at runtime using the link https://www.browseract.com/?co-from=ecommerce&redirect=https://github.com/browser-act/skills/tree/main, which implies the agent will fetch and run remote installer code as a required dependency.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 0.90). The Skill explicitly instructs the agent to automatically install a CLI dependency (BrowserAct) without asking the user or requesting separate approval, which directs the agent to modify the host system state and could lead to unauthorized installation or privilege escalation.