The Agent Skills Directory

[SAFE]: No malicious patterns or security vulnerabilities were detected in the skill instructions or associated reference files.
[COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute Python scripts for figure generation (generate_schematic.py, generate_image.py) and LaTeX for report compilation (xelatex). These commands are standard for the skill's documented functionality and do not exhibit malicious intent (SKILL.md).
[INDIRECT_PROMPT_INJECTION]: The skill processes user-provided content and external research data, presenting an attack surface for indirect prompt injection.
Ingestion points: User-provided paper titles, descriptions for schematic generation, and external literature data retrieved via the research-lookup skill (SKILL.md).
Boundary markers: The instructions do not specify the use of delimiters or markers to isolate untrusted data from system prompts (SKILL.md).
Capability inventory: The skill has the capability to execute shell commands and compile documents using the Bash tool (SKILL.md).
Sanitization: The skill instructions do not include steps for sanitizing or validating user input before it is used in command execution or document generation (SKILL.md).

scientific-writing