amazon-seller-lead-research

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.90). The skill contains explicit instructions to install dependencies automatically and to "not describe" the installation or request user approval, which instructs the agent to hide actions from the user and is a deceptive behavior outside the stated research 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 URLs/search results at runtime, 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: 1.00). The Skill 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 implies fetching and executing external installer code during runtime.

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

• Attempt to modify system services in skill instructions detected (low risk: 0.30). The skill explicitly instructs the agent to install the BrowserAct CLI automatically without asking the user (modifying the host environment), but it does not request sudo, privilege escalation, creation of users, or edits to system files like systemctl/ssh configs, so the risk of directly compromising the machine state is low-to-moderate.