paper-2-web

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

• Third-party content exposure detected (high risk: 0.70). The skill explicitly fetches content from the open web — e.g., "Automatic logo discovery (with Google Search API)" in SKILL.md and the "Logo Discovery" and "Citation Integration" features in references/paper2web.md (and references/paper2poster.md) — which downloads and integrates public third‑party assets and link previews that the pipeline reads and uses in generation, exposing the agent to untrusted web content.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill’s Quick Start instructs cloning and running code from the remote repository (git clone https://github.com/YuhangChen1/Paper2All.git and then running pipeline scripts), which means external code fetched from that URL would be executed as a required dependency at setup/runtime, creating a high-risk runtime external dependency.