The Agent Skills Directory

[SAFE]: No security issues detected. The skill logic is self-contained and focuses on task coordination and structural validation of local graph configurations.
[DYNAMIC_EXECUTION]: The script scripts/test_validate_graph.py uses importlib.util to load the bundled scripts/validate_graph.py module for unit testing. This is a standard development practice for testing local scripts and does not involve untrusted or remote code execution.
[INDIRECT_PROMPT_INJECTION]: The skill ingests work-graph data in JSON format. While this creates a potential surface for injection, the provided scripts/validate_graph.py enforces strict structural validation, cycle detection, and path alias normalization (NFKC) to ensure the agent only processes valid, safe graph states.

agentic-graphs