pp-ankiweb

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

• Third-party content exposure detected (high risk: 0.75). The required workflow runs ankiweb-pp-cli in --agent mode, which fetches public shared deck content (outsider-authored titles/reviews/deck metadata) from AnkiWeb at runtime and returns it as JSON on stdout for the agent/LLM to ingest, creating an indirect prompt-injection surface.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill's prerequisite install steps instruct fetching and running remote code — e.g. npx -y @mvanhorn/printing-press-library install ankiweb --cli-only and go install github.com/mvanhorn/printing-press-library/library/education/ankiweb/cmd/ankiweb-pp-cli@latest — and the CLI is a required dependency, so these external fetches would execute remote code during setup/runtime.