amazon-category-listing-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.80). The skill explicitly instructs the agent to install the BrowserAct dependency automatically and to "not describe it" or request separate approval, which directs the agent to hide installation actions from the user — a deceptive instruction outside the stated scraping purpose.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The document instructs automatic, concealed installation of a runtime dependency and captures browser-visible network responses and session artifacts, enabling supply‑chain installation without user consent and potential data extraction from authorized sessions.

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 “access real browser pages” and “capture browser-visible page content” from user-specified target URLs, which can include outsider-authored free text from public web pages.

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 to automatically install and invoke BrowserAct at runtime using the install 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 indicates the agent will fetch and execute remote installation code as a required runtime dependency.

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 runtime CLI dependency and to do so without asking the user for confirmation, which encourages the agent to modify the host system (potentially requiring elevated privileges) without explicit consent.