The Agent Skills Directory

[SAFE]: The skill processes data from GitHub issues to create visual dependency graphs. It includes a dedicated validation layer in plan-dag-render.py that checks for forbidden characters and structural integrity of the input data before rendering.
[COMMAND_EXECUTION]: The skill invokes the dot utility from the Graphviz suite and the node runtime for rendering. These calls are made using subprocess.run with list-based arguments, which prevents shell injection by avoiding the use of a shell for execution.
[EXTERNAL_DOWNLOADS]: The skill relies on standard tools like graphviz and playwright. These are well-known, reputable software packages commonly used for diagramming and browser automation. The installation instructions provided for the user follow best practices.
[PROMPT_INJECTION]: No malicious prompt injection patterns were detected in the instructions or metadata. The skill instructions focus strictly on its stated purpose of assisting with project planning and visualization.

plan-dag