The Agent Skills Directory

[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface by ingesting untrusted project files and content sources to guide presentation generation. \n- Ingestion points: Phase 1 (Gather Context) involves reading project files, paper drafts, and notes. \n- Boundary markers: Absent; the instructions do not implement delimiters or safety warnings to ignore instructions embedded in the source materials. \n- Capability inventory: The skill has access to Bash(python*), Bash(R*), Bash(Rscript*), and file write capabilities. \n- Sanitization: No sanitization or validation of input data is defined before the information is processed by the agent. \n- [COMMAND_EXECUTION]: The skill workflow requires executing Python and R scripts in the local environment to generate figures and using LaTeX compilation tools (pdflatex, xelatex). While these are core functionalities, they constitute a command execution surface.

beamer-deck