pp-averusa

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

• Third-party content exposure detected (medium risk: 0.30). The required runtime workflow (“Agent Mode” and “Automatic learning”) ingests outsider-authored free text via the user question passed to averusa-pp-cli recall "<user's question>" --agent, which then drives subsequent reads/searches over the harvested catalog.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill requires fetching and installing remote Go modules that produce and execute the averusa-pp-cli/averusa-pp-mcp binaries (github.com/mvanhorn/printing-press-library/... shown below), so runtime depends on executing code retrieved from those external locations.