The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute local Python scripts (scripts/generate_schematic.py and skills/scientific-slides/scripts/pdf_to_images.py) to facilitate document processing and scientific visualization tasks.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external documents (manuscripts, grants, and PDFs) which represents a surface for indirect prompt injection attacks. 1. Ingestion points: Scientific manuscripts and PDF presentation files processed by the agent. 2. Boundary markers: The skill lacks explicit instructions or delimiters to prevent the agent from obeying potentially malicious commands embedded within research documents. 3. Capability inventory: The skill has access to the Read, Write, Edit, and Bash tools. 4. Sanitization: No input validation or sanitization is described for the text extracted from documents before it is used in the evaluation workflow.

peer-review