hf-papers-reporter

Warn

Audited by Snyk on Feb 19, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). The SKILL.md and scripts explicitly scrape huggingface.co/papers and download arXiv PDFs and Hugging Face CDN images (see "Fetch Paper List" in SKILL.md and the download_pdf / download_cover_image functions), and the agent parses abstracts/introduction from those public papers as part of its workflow, so untrusted third‑party content directly influences which papers are processed and what the tool outputs.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 19, 2026, 03:58 PM