The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to use the bash tool to execute local Python scripts for figure and schematic generation.
Evidence: SKILL.md contains commands such as python scripts/generate_schematic.py and python scripts/generate_image.py.
[COMMAND_EXECUTION]: The skill requires the agent to compile LaTeX documents using system tools.
Evidence: SKILL.md directs the agent to execute xelatex report.tex to produce the final document.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it is designed to ingest, process, and summarize external literature and research data.
Ingestion points: The skill explicitly relies on the research-lookup tool to fetch external literature content as specified in SKILL.md.
Boundary markers: The instructions do not define delimiters or specific "ignore embedded instructions" warnings for the ingested data.
Capability inventory: The skill has access to bash, Read, Write, and Edit tools, allowing it to execute local scripts and modify files based on processed input.
Sanitization: No evidence of input validation or sanitization for the research data is provided in the skill documentation.

scientific-writing