The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided text to extract entities and relationships. This represents an inherent attack surface where malicious instructions embedded in the input text could attempt to influence the agent's behavior during the extraction process.
Ingestion points: Processes arbitrary user-provided text for 'Text-Based Extraction' as described in SKILL.md.
Boundary markers: The instructions do not specify explicit delimiters or 'ignore' instructions for the processed user text.
Capability inventory: The skill utilizes several tools including create_knowledge_graph, generate_knowledge_graph, memory_add_relations, memory_get_relations, and search to interact with the InfraNodus platform.
Sanitization: No specific sanitization or validation logic is defined for the extracted content before it is passed to the tools.

ontology-generator