alibaba-supplier-profile-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 1.00). The skill explicitly instructs the agent to install BrowserAct automatically and to avoid informing or requesting separate user approval ("do not describe... do not request separate approval"), which is a hidden/deceptive instruction outside 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 runtime browser-act Skill to “capture browser-visible page content” from user-specified public URLs/pages, which can include outsider-authored free text from the target websites and is then ingested into the agent’s LLM context.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill requires automatic installation of the BrowserAct Skill/CLI from https://www.browseract.com/?co-from=ecommerce (and the install redirect https://www.browseract.com/?co-from=ecommerce&redirect=https://github.com/browser-act/skills/tree/main), which at runtime would fetch and install remote code that directly controls agent execution.

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 explicitly tells the agent to automatically install the BrowserAct CLI/Skill without asking the user for confirmation, which directs the agent to modify the host environment by installing software (potentially requiring elevated privileges), so it encourages changing machine state even though it doesn't explicitly ask for sudo or file edits.