The Agent Skills Directory

[SAFE]: The skill utilizes a set of internal graph navigation and analysis tools such as semantic_search_nodes_tool, query_graph_tool, get_flow, detect_changes_tool, and get_impact_radius_tool. These tools are used for legitimate debugging purposes.
[SAFE]: No instances of data exfiltration or sensitive information exposure were found. The skill does not access credentials, private keys, or perform network requests to external domains.
[SAFE]: There are no prompt injection attempts or instructions designed to bypass agent safety protocols or override system behavior.
[SAFE]: No code obfuscation, dynamic execution, or remote script downloads (e.g., curl | bash) are present in the skill instructions.

Debug Issue