linkedin-job-search-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (medium risk: 0.30). The skill contains instructions to automatically install a required CLI dependency without user confirmation, which represents a medium-severity security boundary circumvention pattern.

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

• Third-party content exposure detected (low risk: 0.10). The workflow scrapes public LinkedIn job search results and profiles via a browser automation tool, which involves ingesting web page text that can contain outsider-authored content.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs the agent to automatically download and install missing runtime dependencies from an external repository locator without user confirmation, presenting a weak or unknown third-party operational dependency.