paper-analysis-assistant
Pass
Audited by Gen Agent Trust Hub on May 19, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill downloads PDF documents from arXiv's official website using the
requestslibrary inscripts/download_pdf.py. - This operation is performed through the
arxiv.orgdomain, which is a well-known academic repository. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by processing untrusted external PDF content and interpolating it into an HTML report without sanitization.
- Ingestion points: External data enters the system through
scripts/download_pdf.py(fetching from arbitrary arXiv URLs) and is processed byscripts/extract_text.pyto createpaper.txt. - Boundary markers: No delimiters or isolation instructions are used when embedding the extracted paper content into the HTML template in
scripts/generate_html.py. - Capability inventory: The skill includes scripts capable of network requests (
scripts/download_pdf.py), file system writes across multiple formats (scripts/generate_html.py,scripts/generate_ppt.py), and system speech engine interaction (scripts/text_to_speech.py). - Sanitization: There is no evidence of HTML escaping or content filtering in
scripts/generate_html.pybefore the extracted paper text is written to the output file.
Audit Metadata