alphaxiv
Pass
Audited by Gen Agent Trust Hub on Apr 19, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill processes data from external academic sources which may contain instructions targeting the agent (Indirect Prompt Injection).
- Ingestion points: Paper overviews, full markdown, and LaTeX source files are retrieved from alphaxiv.org and arxiv.org (SKILL.md).
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the workflow.
- Capability inventory: The skill utilizes Bash, WebFetch, and Write capabilities (SKILL.md).
- Sanitization: No content filtering or sanitization is applied to the retrieved academic text before processing.
- [EXTERNAL_DOWNLOADS]: Fetches academic paper content and source archives from well-known repositories.
- Fetches markdown summaries and full text from AlphaXiv's official domain.
- Downloads LaTeX source archives (.tar.gz) from arXiv's official repository for deep inspection of paper details.
Audit Metadata