The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests network service data from external Cisco NSO controllers using tools like get_service_types and get_services (SKILL.md). This data is then used to generate reports and interact with integrated tools such as github-ops and Slack. The absence of boundary markers or sanitization guidelines creates a surface where malicious service names or metadata could influence the agent's behavior during report generation or repository commits. * Ingestion points: Service names, types, and instance metadata fetched from the NSO API. * Boundary markers: None provided in the agent instructions. * Capability inventory: Repository commits via github-ops, messaging via Slack and MS Teams, and device state checks via nso-device-ops. * Sanitization: No sanitization or validation logic is specified for the ingested network data.
[COMMAND_EXECUTION]: The skill utilizes the cisco-nso-mcp-server command (SKILL.md), which is the primary execution entry point for the MCP server and is intended to be pre-installed via pip.

nso-service-mgmt