alphaxiv-paper-lookup

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to fetch and consume AI-generated overviews and full paper text from public third-party endpoints (e.g., https://api.alphaxiv.org/papers/v3/{PAPER_ID}, https://api.alphaxiv.org/papers/v3/{VERSION_ID}/overview/{LANG}, and https://alphaxiv.org/abs/{PAPER_ID}.md), so untrusted external content is read and directly used to drive the agent's outputs and decisions.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill makes runtime fetches of external content (e.g., https://api.alphaxiv.org/papers/v3/{VERSION_ID}/overview/{LANG} and https://alphaxiv.org/abs/{PAPER_ID}.md) and injects the returned "intermediateReport"/overview text into the model context to drive its responses, so the remote content directly controls prompts and is a required dependency.