The Agent Skills Directory

[SAFE]: The skill employs local Python scripts (repo_snapshot.py and create_excalidraw_scene.py) to summarize codebase structures and generate Excalidraw JSON scenes. These scripts utilize standard libraries for file system operations and data formatting, consistent with the stated purpose.\n- [SAFE]: No evidence of credential harvesting, unauthorized network communication, or code obfuscation was detected. The skill's instructions recommend best practices for managing API endpoints and credentials.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes external code and documentation to create diagrams (ingestion points: repo_snapshot.py reads repository file contents; capability inventory: local script execution and file writing; boundary markers: absent; sanitization: absent). This creates a vulnerability surface for indirect prompt injection, but the risk is managed as the tools perform structural analysis rather than code execution, which is appropriate for the skill's primary visualization use case.

excalidraw-learning-aids