The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute local Python scripts using the Bash tool to generate schematics and process presentation files.
Evidence: python scripts/generate_schematic.py "your diagram description" -o figures/output.png in SKILL.md.
Evidence: python skills/scientific-slides/scripts/pdf_to_images.py presentation.pdf review/slide --dpi 150 in SKILL.md.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes external, untrusted scientific documents (manuscripts and presentations) while having access to sensitive tools such as Bash, Write, and Edit.
Ingestion points: Scientific manuscripts, grant proposals, and PDF slide decks provided by users for review.
Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore potentially malicious instructions embedded within the text of the manuscripts.
Capability inventory: The skill uses Read, Write, Edit, and Bash tools, allowing it to perform file operations and execute shell commands.
Sanitization: The skill provides a specific security/stability mitigation by mandating that presentation PDFs be converted to images for visual review rather than being read as text, which reduces the risk of the agent following instructions embedded directly in the PDF content.

peer-review