xray-paper-skill

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow (SKILL.md Step 1) explicitly fetches and ingests web pages ("Web URL / arXiv abs / alphaxiv page: fetch the page with WebFetch") and then reads and interprets that untrusted third-party content as part of its analysis, so arbitrary webpage content could materially influence the agent's decisions or outputs.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill declares it will fetch arbitrary web paper URLs at runtime (e.g., https://arxiv.org/abs/2401.12345) and inject the fetched page text into the agent's analysis context, so remote content can directly control prompts/behavior.