alphaxiv
Warn
Audited by Snyk on Mar 10, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill directly fetches and prints content from the public AlphaXiv API (e.g., api.alphaxiv.org via endpoints like /papers/v3/{id}, /papers/v3/{id}/overview, /papers/v3/{id}/implementations and /papers/v3/feed) as shown in SKILL.md and scripts/alphaxiv.py, and that content includes community/AI-generated abstracts, comments, implementations and overviews which the agent reads and returns (and is used in the ask/chat flow), so untrusted third‑party content can influence the agent's outputs.
Audit Metadata