pp-crestron

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

• Third-party content exposure detected (medium risk: 0.30). The runtime workflow is the Crestron Printing Press CLI in “Agent Mode” plus the “Automatic learning” loop, where it ingests the user-provided question via crestron-pp-cli recall "<user's question>" --agent and then reads/executes structured “candidates/playbook/notes” derived from prior learning, meaning outsider-authored free text can flow into the agent’s decision path.

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 commands invoke remote installers that fetch and execute code at runtime (e.g., "npx -y @mvanhorn/printing-press-library install crestron --cli-only" and "go install github.com/mvanhorn/printing-press-library/library/devices/crestron/cmd/crestron-pp-cli@latest"), and the CLI fetched this way is a required runtime dependency.