The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external Neo4j databases. This creates a surface for indirect prompt injection where data retrieved from the database (e.g., node properties or graph results) could contain malicious instructions intended to influence the agent's downstream behavior.
Ingestion points: External database content retrieved via the read-cypher tool and Python stream methods as described in SKILL.md.
Boundary markers: None identified in the provided instructions to delimit or ignore instructions embedded within retrieved data.
Capability inventory: The skill utilizes write-cypher for database modifications, Bash for environment setup, and WebFetch for external documentation access as defined in SKILL.md.
Sanitization: No specific sanitization or validation logic for external data is prescribed in the skill instructions.

neo4j-gds-skill