The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes user-controlled text within its prompt generation logic without adequate isolation.
Ingestion points: The topic command-line argument in scripts/generate_diagram.py serves as the entry point for untrusted user data.
Boundary markers: Absent. The user input is interpolated directly into the meta_prompt string using f-strings without the use of delimiters (like XML tags or triple quotes) or instructions to ignore embedded commands.
Capability inventory: The skill possesses the capability to write files to the local filesystem using the Pillow library's save method in scripts/generate_diagram.py.
Sanitization: Absent. No validation, escaping, or filtering is applied to the user-supplied topic before it is included in the prompt sent to the Gemini API.

diagram-generator