hugging-face-paper-publisher
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes research paper metadata (titles, abstracts, and authors) fetched from the external arXiv API and user-provided inputs, which are then interpolated into markdown templates and Hugging Face repository README files.
- Ingestion points: Metadata is retrieved from the arXiv API via
PaperManager.get_arxiv_infoand through CLI arguments like--titleand--abstractinscripts/paper_manager.py. - Boundary markers: The skill uses HTML comment markers
<!-- paper-manager:start -->and<!-- paper-manager:end -->to delimit generated content when updating repository READMEs. - Capability inventory: The skill performs file writes to the local filesystem, makes network requests to external APIs, and uses the
huggingface_hublibrary to upload modified files (README updates) to user repositories. - Sanitization: The script implements
_sanitize_textto neutralize markdown code fence breakouts and YAML document delimiters, and_escape_yaml_valueto wrap strings in quotes and escape internal characters, reducing the risk of injection attacks from untrusted paper metadata. - [COMMAND_EXECUTION]: The skill's primary functionality is delivered through a CLI script (
scripts/paper_manager.py) intended to be executed by the user viauv runor standard Python, involving various operations such as indexing, linking, and creating research articles. - [EXTERNAL_DOWNLOADS]: The skill fetches paper metadata from the well-known arXiv service (
export.arxiv.org) and interacts with Hugging Face Hub (huggingface.co) to retrieve and update repository contents.
Audit Metadata