The Agent Skills Directory

[COMMAND_EXECUTION]: The skill directs the agent to construct and execute shell commands via the Bash tool. In SKILL.md, the agent is instructed to run python scripts/generate_schematic.py and python scripts/generate_image.py using natural language descriptions as command-line arguments.
[PROMPT_INJECTION]: The skill exhibits a significant Indirect Prompt Injection surface. It is designed to ingest and process untrusted data from external sources using the research-lookup tool. * Ingestion points: Data entering through the research literature search workflow described in SKILL.md. * Boundary markers: Absent. There are no instructions to delimit fetched data or ignore potential instructions embedded within the research material. * Capability inventory: The skill has access to Bash, Write, Read, and Edit tools, and is explicitly instructed to use them to generate files and run scripts. * Sanitization: Absent. The skill instructs the agent to interpolate user-influenced or data-influenced descriptions directly into shell commands without escaping or validation.
[EXTERNAL_DOWNLOADS]: The skill references and mandates the use of external Python scripts (scripts/generate_schematic.py and scripts/generate_image.py) and several other unverified skills (scientific-schematics, generate-image, research-lookup) that are not included in the provided file set.

scientific-writing