The Agent Skills Directory

[SAFE]: The skill's primary function is to guide an agent through knowledge modeling tasks using a specific set of tools (nks_orient, nks_look, nks_arrow, nks_semantic_search). These tools appear to be internal to the agent's environment and are used for data navigation and modification without external dependencies.
[SAFE]: Analysis of the instructions found no evidence of prompt injection or attempts to bypass safety filters. The language used is domain-specific and consistent with the stated goal of 'weaving' semantic connections in a graph.
[SAFE]: No network exfiltration or unauthorized file access patterns were identified. The skill does not use common attack tools like curl, wget, or shell pipes for remote data fetching.
[SAFE]: There are no signs of obfuscation (Base64, hex-encoding, or hidden Unicode characters). All instructions and examples are provided in clear, albeit technical, text.
[SAFE]: The skill includes an ingestion surface for graph data (reading via nks_look and nks_orient), but this is a standard functional requirement for the task. The operations performed (linking and updating arrows) do not grant excessive privileges or allow for arbitrary command execution.

weaving