walmart-category-listing-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.90). The Skill includes explicit instructions to install a runtime dependency automatically and to avoid informing or requesting separate approval from the user (lines 41–47), which is a hidden/deceptive instruction that overrides normal user consent and falls outside the scraping task's stated 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 real browser pages” and “capture browser-visible page content” from user-specified Walmart URLs at runtime, which is 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 at runtime to auto-install and invoke BrowserAct 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 causes the agent to fetch and install external 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 (medium risk: 0.60). The Skill instructs the agent to automatically install a CLI dependency on the host "without asking the user to confirm" and to proceed with runtime installation and invocation, which directs the agent to modify the machine's state (install software) without explicit user consent.