create-marp-deck

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

• Third-party content exposure detected (high risk: 0.90). The skill's Phase 1 interview explicitly directs the agent to "read/fetch" user-provided files, URLs, or references "thoroughly before continuing" (SKILL.md, Phase 1 — Question 3), which means arbitrary public web pages or user-generated content would be ingested and could influence generation and subsequent actions.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill runs the export commands "npx @marp-team/marp-cli@latest --no-stdin ..." at runtime to produce HTML/PPTX, which causes npx to fetch and execute remote code from the npm registry and is a required dependency for the export step