deepxiv-cli

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly instructs embedding API tokens in commands and code (e.g., deepxiv config --token YOUR_NEW_TOKEN and Reader(token="YOUR_TOKEN")), which requires the LLM to handle and potentially output secrets verbatim.

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

• Third-party content exposure detected (high risk: 0.80). This skill explicitly fetches and ingests open/public third‑party papers from arXiv and PMC (see SKILL.md commands like deepxiv paper and deepxiv pmc) and uses that content in an integrated agent for analysis, meaning untrusted web-hosted content can influence the agent's behavior and decisions.