The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires cloning a repository from a non-trusted source: https://github.com/YuhangChen1/Paper2All.git. It also instructs the installation of unverified dependencies via pip install -r requirements.txt from this repository.
[COMMAND_EXECUTION]: The skill uses the Bash tool to execute complex transformation pipelines and scripts, such as python pipeline_all.py and python scripts/generate_schematic.py. These scripts handle file manipulation, external process spawning (LibreOffice, Poppler), and external API calls.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it processes untrusted user data (academic papers) to drive LLM-based content extraction and design.
Ingestion points: LaTeX and PDF files provided in the input-dir or paper directories (e.g., SKILL.md, references/paper2web.md).
Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are implemented for the processed paper content.
Capability inventory: The skill utilizes Bash for command execution and Write/Edit for file system modifications across its scripts.
Sanitization: There is no evidence of sanitization or filtering for instructions that might be embedded within the processed LaTeX/PDF source files.

paper-2-web