The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute a local Python script at scripts/render_diagram.py to render diagrams. Since the source code for this script was not included in the provided files, its safety cannot be verified, posing a risk of arbitrary command execution on the host system.
[EXTERNAL_DOWNLOADS]: The skill facilitates the automated installation of the Mermaid CLI tool via npm install -g @mermaid-js/mermaid-cli. While this targets a well-known package registry, it performs a global installation that modifies the system environment.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process natural language, notes, schemas, and code snippets from the user to generate diagrams. This creates a surface where malicious instructions embedded in the input data could attempt to manipulate the agent's workflow.
Ingestion points: Processes natural language, notes, code, and schemas as described in SKILL.md.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands within the input data were identified.
Capability inventory: The skill has the ability to execute local scripts and install external packages.
Sanitization: There is no evidence of input validation or sanitization before the data is processed for diagram generation.

diagram-generator