pp-dndbeyond

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

• Third-party content exposure detected (medium risk: 0.30). The runtime workflow for this skill reads outsider-authored free text when the user pipes arbitrary Beyond20/D&D Beyond JSON snapshots or exported PDFs into dndbeyond-pp-cli characters inspect via --file/--stdin, and the agent mode then processes that content.

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 fetch and install remote Go modules that will be built/executed and are required for the skill (e.g., github.com/mvanhorn/printing-press-library/library/developer-tools/dndbeyond/cmd/dndbeyond-pp-cli@latest and github.com/mvanhorn/printing-press-library/library/developer-tools/dndbeyond/cmd/dndbeyond-pp-mcp@latest), so this is a runtime external dependency that results in executing externally fetched code.