neo-user-journey

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

• Third-party content exposure detected (high risk: 0.75). The required runtime workflow is installing/invoking the neo-user-journey skill from the public GitHub repo, which (by its description) runs Playwright against live/localhost URLs and uses scraped page/test content as input to the agent’s LLM context—i.e., outsider-authored free text from arbitrary web pages/URLs.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly directs runtime installation via "npx skills add Cornjebus/neo-user-journey" which pulls and installs code from the upstream GitHub repo (https://github.com/Cornjebus/neo-user-journey) that would be executed as the skill and thereby control agent behavior.