pp-dndbeyond

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

• Third-party content exposure detected (low risk: 0.10). The skill reads public D&D Beyond rules pages and user-supplied character snapshots, which are active fetches of external content or local user files rather than monitored unsolicited outsider feeds.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs the agent to install an external binary from GitHub using go install and npx, constituting a remote operational dependency with third-party unofficial provenance.