paper-2-web
Warn
Audited by Gen Agent Trust Hub on Apr 16, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to clone a repository from an external source (GitHub: YuhangChen1/Paper2All) which is not a pre-approved or official vendor repository.
- [REMOTE_CODE_EXECUTION]: Following the repository clone, the skill executes downloaded scripts (python pipeline_all.py) and installs third-party dependencies from a requirements file.
- [COMMAND_EXECUTION]: The skill utilizes Bash tools to perform environment setup, repository cloning, and pip package installations.
- [PROMPT_INJECTION]: The skill processes external documents (PDF/LaTeX) and uses an LLM pipeline for content extraction, presenting a risk of indirect prompt injection. Ingestion points: input papers in LaTeX or PDF format. Boundary markers: No delimiters or ignore instructions for embedded content are specified in the prompt instructions. Capability inventory: The skill has access to Bash, Write, Edit, and Read tools. Sanitization: No input validation or sanitization of paper content is described.
Audit Metadata