The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it transforms user-supplied text into diagram elements. Ingestion points: Untrusted text content provided by the user (SKILL.md). Boundary markers: Absent; the skill does not define specific delimiters for separating input data from instructions. Capability inventory: The skill utilizes the 'Write' tool to save generated content to the local file system (SKILL.md). Sanitization: Present; it performs character replacement for double quotes and parentheses to maintain JSON structure and formatting.
[COMMAND_EXECUTION]: The skill instructs the agent to use a file-writing tool to automatically save generated diagrams to the current working directory, which is a standard functional requirement for this type of utility.

excalidraw-diagram