1688-search-results-scraper

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (low risk: 0.10). The skill extracts arbitrary web pages and search results via BrowserAct, which involves reading outsider-authored content from web listings (low risk).

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs automatic installation of an external skill repository from an unverified third-party promotional redirect URL, representing a weak/unknown operational dependency.

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

• Attempt to modify system services in skill instructions detected (high risk: 1.00). The skill prompt instructs the agent to automatically download and execute remote installation scripts without user confirmation if a dependency is missing, which poses a security risk.