aliexpress-search-results-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.90). The skill explicitly instructs the agent to install a runtime dependency automatically and to "not request separate approval" or describe it as a browser request, which directs the agent to hide/avoid user consent and is deceptive relative to expected transparent behavior.

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 (AliExpress search/result pages) into the LLM context via BrowserAct.

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

• Potentially malicious external URL detected (high risk: 0.80). The Skill explicitly directs the agent at runtime to obtain and automatically install/use the BrowserAct CLI from https://www.browseract.com/?co-from=ecommerce (and the redirect variant), which implies fetching and executing remote installation code that controls the agent's runtime behavior.

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

• Attempt to modify system services in skill instructions detected (high risk: 0.70). The skill instructs the agent to automatically install a required CLI dependency without asking the user for confirmation (and to proceed after installation), which pushes the agent to modify the host environment and could trigger privileged operations or other state changes.