pp-ankiweb

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

• Third-party content exposure detected (high risk: 0.72). The required runtime workflow is executing the ankiweb-pp-cli binary (e.g., shared search/info/download), which fetches public shared-deck catalog/content from AnkiWeb at runtime; that outsider-authored free text (deck titles/descriptions/reviews or other scraped/provided prose) can be ingested into the agent’s LLM context via the CLI’s JSON output when --agent is used.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill requires installing and running a third-party CLI by fetching and executing remote code (via "npx -y @mvanhorn/printing-press-library install ankiweb --cli-only" and the Go install target "github.com/mvanhorn/printing-press-library/library/education/ankiweb/cmd/ankiweb-pp-cli@latest"), which are runtime external dependencies that execute remote code on the agent.