huggingface-papers
Warn
Audited by Snyk on Aug 26, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The skill ingests outsider-authored free text at runtime when a user-provided Hugging Face paper/arXiv URL or ID is used to fetch the corresponding paper content as markdown (e.g.,
https://huggingface.co/papers/{PAPER_ID}.mdor the fallback arXiv HTML/PDF) and then summarized/explained/analyzed by the LLM.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata